24 results about "Fuzzy clustering analysis" patented technology

The invention relates to the field of drip irrigation regulation and control, in particular to an accurate regulation and control method for corn root layer nitrogen under the drip irrigation condition, which comprises the following steps: standardizing multi-source remote sensing soil data of a land parcel to obtain soil grid points, and evaluating the crop growth adaptive relative grade of the grid points; carrying out factor modeling and self-adaptive grading on the soil erodibility parameters to obtain soil fertility potential grades of the grid points; carrying out fusion evaluation on global attribute fluctuation and spatial heterogeneity to obtain adaptive spatial context weight factors of the grid points; performing fusion evaluation on the adaptive spatial context weight factors of the grid points and the soil fertility potential levels of the grid points to obtain gradient consistency distance measurement between the grid points; fuzzy clustering analysis is carried out through gradient consistency distance measurement between grid points to obtain an optimized management partition map and a differentiated drip irrigation strategy, so that the control complexity of a drip irrigation pipe network is reduced, and the drip irrigation precision and the fertilization efficiency are improved.

The invention provides a power grid load cluster classification method based on a fuzzy clustering method, and belongs to the technical field of power grid regulation and control. Comprising the following steps: according to real-time updated dynamic historical power data of to-be-classified load equipment, obtaining power data statistical characteristics of each load equipment in a target time window; carrying out fuzzy clustering analysis on the load equipment of the target time window by combining the equipment attribute and the power data statistical characteristic of each load equipment and inheriting the clustering parameter of the last time; updating a tag knowledge base according to a clustering result, wherein the tag knowledge base stores a clustering cluster center vector and a corresponding load attribute tag; and sliding the time window backwards, returning to the starting step for repeated execution, and outputting the classified load clusters aiming at the current power data and the load attribute label of each cluster when execution is performed to the last time window. According to the invention, by analyzing and processing the power utilization data accumulated in the operation process of different load devices, the load clusters with different power utilization habits can be divided.

The present invention discloses a network security situation assessment method that integrates fuzzy cluster analysis and fuzzy comprehensive evaluation and decision-making, which relates to the field of network security technology. The method includes: first, obtaining an initial data matrix, then using the translation-range transformation method to standardize it, then constructing a fuzzy similarity matrix through the similarity coefficient-quantity product method, then obtaining a fuzzy equivalence matrix based on the closure transfer characteristic, and performing dynamic clustering to construct a first-level situation factor set and a second-level situation factor set; then, based on expert advice, obtaining a single-factor fuzzy mapping set of characteristic attributes of each cluster, and using the hierarchical analysis method to obtain the corresponding weight vector; using a weighted average operator to calculate the fuzzy comprehensive evaluation matrix, and then obtaining the status of the network security situation through the maximum membership principle. Therefore, the above method can comprehensively consider the fuzzy interactions and weight distribution of each clustering factor to achieve network security situation assessment, and the assessment framework is more flexible and adaptable.

The application discloses a kind of multi-river confluence material source source-sink analysis method and analysis device, and multi-river confluence material source source-sink analysis method includes: obtaining the content of each heavy mineral in each mineral sample in research area, and research area is the collection area of multiple rivers;According to the heavy mineral assignment formula, the sum of the heavy mineral content of each mineral sample is calculated, and the mineral samples in the research area are classified according to the calculation result, and the source direction of each type of mineral is analyzed;According to the classification result of mineral sample, the ratio method is used to cluster analysis on the mineral sample in each type of mineral, and a cluster diagram is obtained;Based on the cluster diagram, and combined with the source direction of each type of mineral and the geological characteristics of research area, the source direction of each mineral sample in each type of mineral in research area is determined by using fuzzy cluster analysis method;It can further finely divide the source direction, improve the accuracy of source source-sink analysis result, and the analysis operation convenience.

The invention relates to a cross-border customer accurate portraying and predicting method based on integrated fuzzy clustering and a decision tree. The method comprises the following steps of performing customer feature classification and preprocessing; training the reference model, and extracting feature importance; standardizing the selected important feature set, and performing dimensionality reduction on standardized features by adopting principal component analysis; performing fuzzy clustering analysis; carrying out feature fusion, retraining the XGBoost model, and extracting important feature indexes; and screening and generating a customer portrait. According to the cross-border customer accurate portraying and predicting method, system and device based on the integrated fuzzy clustering and decision tree, the processor and the computer readable storage medium thereof, the fuzzy membership degree vector is added, so that the recognition capability of edge customers is improved, the limitation of a traditional label model is made up, the labor cost is reduced, the clue quality is improved, and the user experience is improved. The system has good expandability and integration, and has generalization for complex financial products.

The application discloses a kind of based on fuzzy clustering and reinforcement learning's time sequence knowledge graph inference method and system, the method includes: based on fuzzy clustering algorithm to the entity in time sequence knowledge graph is fuzzy clustering analysis, each entity is mapped to multiple clustering clusters, reinforcement learning environment is constructed based on clustering cluster, and based on search strategy control agent searches reinforcement learning environment, candidate action space is generated based on the action in the process of agent search, and the candidate action in candidate action space is scored, obtains the target score of candidate action, target score is converted into the action selection probability of agent strategy network, the action selection probability is used to drive agent to select action, based on the target entity searched by agent to the missing component of quadruple in time sequence knowledge graph is predicted, to significantly reduce the redundancy of agent search action space, improve agent decision efficiency, effectively improve the inference efficiency and accuracy of time sequence knowledge graph.

The invention belongs to the field of accident risk grading, and relates to a dangerous goods transportation leakage accident consequence risk grading evaluation method based on accident range area simulation, and the method comprises the steps: obtaining data information after a traffic accident; inputting the data information into the accident range area simulation model to obtain an accident consequence index; performing clustering analysis on the accident consequence indexes by adopting a K-means algorithm to obtain a dangerous goods transportation leakage accident consequence risk grading result; evaluating an accident consequence risk grading result; determining the severity and the influence range of the accident consequence according to the evaluation result; constructing a three-dimensional comprehensive risk evaluation matrix, querying three grading matrixes, obtaining corresponding risk grades, and performing comprehensive risk grade evaluation; carrying out fuzzy clustering analysis to obtain a transportation road section risk grade, and defining a road section risk value as a product of a road section grade and a road section length; calculating the risk value of the transportation route by using the thought of a triangular fuzzy number; screening the transportation routes according to the risk values to obtain an optimal transportation route of the dangerous goods; the risk grading evaluation model can be continuously optimized and perfected by establishing a feedback mechanism, and the accuracy and reliability of an evaluation result are improved.

This invention relates to a method for assessing the operational status of distribution networks based on interval type-two fuzzy clustering analysis. By employing an interval type-two c-means fuzzy clustering method based on local fuzzy metrics in the boundary region, it incorporates data imbalance factors into the cluster center update calculation function. This ensures that the cluster centers are related not only to the membership function of the imbalanced dataset but also to the degree of imbalance between clusters. The interval type-two fuzzy c-means clustering algorithm is used to calculate, analyze, and cluster data samples in the boundary region. An optimized cluster center update function considering local fuzzy metrics in the boundary region is introduced, improving the aggregation and clustering effect of the interval type-two fuzzy c-means clustering method on imbalanced operational data of distribution networks. This invention applies the improved aggregation and clustering algorithm to analyze frequently alarming imbalanced data in distribution networks, assessing the operational status of the distribution network. It not only identifies the types of alarm faults that have occurred but also predicts the probability of future alarms in the distribution network.

The application discloses a retired battery screening method and device based on fuzzy clustering analysis, and a medium. The method comprises the following steps: obtaining the charge-discharge data of a retired battery cell to be screened; training a feedforward neural network according to the charge-discharge data; fitting an incremental capacity curve corresponding to the retired battery cell based on the trained feedforward neural network; constructing a multi-dimensional health feature corresponding to the retired battery cell according to the incremental capacity curve; generating a battery dataset carrying a battery classification label according to the distribution relationship between the health state value output by the health state estimation model and the preset health state threshold; determining an initial clustering center based on the probability density of each sample point in the battery dataset; inputting the initial clustering center and the battery dataset into a preset semi-supervised fuzzy C-means clustering model for iterative calculation, so as to classify and screen the retired battery cell according to the output clustering result.

The invention relates to a view clustering analysis method and device, computer equipment, a computer readable storage medium and a computer program product. The method comprises the following steps: acquiring an original view data set; according to the view type of each view in the original view data set, a target domain division algorithm is determined, each view is processed according to the domain number of each scale level through the target domain division algorithm, and a label indication matrix of each view under each scale level is obtained; based on the label indication matrix of each view under each scale level, determining each domain feature under each scale level; performing fuzzy clustering analysis on each domain feature to obtain a space-level membership matrix under each scale level; and determining a clustering result indication matrix of the original view data set based on the space-level membership matrix, the tensor low-rank item and the clustering indication learning item under each scale level. By adopting the method, the calculation efficiency can be improved while the clustering precision is improved, and the flexibility can also be improved.

The invention provides an edible agricultural product quality safety evaluation method and system based on localized data integration. The method comprises the following steps: constructing a space-time-ecology-society three-dimensional dynamic evaluation model; performing dynamic weight distribution and data fusion on each axis to generate a comprehensive evaluation index and a risk correction coefficient; formulating a differential supervision strategy and an optimal resource allocation scheme according to the index and the coefficient; and performing dynamic early warning on the agricultural product quality safety risk based on the scheme, and outputting a visual two-dimensional comprehensive evaluation report. According to the method, a comprehensive evaluation index is generated by adopting a weighted geometric mean method, a risk correction coefficient is constructed in combination with a correlation coefficient, and a quality safety level boundary is divided through fuzzy clustering analysis, so that an evaluation result is highly matched with an actual risk. And finally, a full-chain closed loop is formed through a supervision strategy library and a resource allocation scheme in combination with a dynamic early warning emergency linkage system, so that the timeliness, accuracy and resource utilization efficiency of agricultural product quality safety assessment are improved, and the actual risk deviation is reduced.

The present invention relates to the field of drip irrigation regulation, and in particular to a method for precise regulation of nitrogen in the root layer of corn under drip irrigation conditions. The method comprises: obtaining soil grid points by standardizing multi-source remote sensing soil data of a plot, and evaluating the adaptive relative grades of crop growth at the grid points; obtaining the soil potential grades of the grid points by factor modeling and adaptive grading of soil erodibility parameters; obtaining the adaptive spatial context weight factors of the grid points by fusing and evaluating global attribute fluctuations and spatial heterogeneity; obtaining the gradient consistency distance measurement between the grid points by fusing and evaluating the adaptive spatial context weight factors of the grid points with the soil potential grades of the grid points; and obtaining an optimized management zoning map and a differentiated drip irrigation strategy by performing fuzzy clustering analysis based on the gradient consistency distance measurement between the grid points, thereby reducing the control complexity of the drip irrigation network and improving the drip irrigation precision and fertilization efficiency.

The invention discloses a time sequence knowledge graph reasoning method and system based on fuzzy clustering and reinforcement learning, and the method comprises the steps: carrying out the fuzzy clustering analysis of entities in a time sequence knowledge graph based on a fuzzy clustering algorithm, mapping each entity to a plurality of clustering clusters, building a reinforcement learning environment based on the clustering clusters, and carrying out the fuzzy clustering analysis of the entities in the time sequence knowledge graph. The method comprises the steps of obtaining a search strategy of an agent strategy network, controlling an agent to search a reinforcement learning environment based on the search strategy, generating a candidate action space based on actions in the agent search process, scoring candidate actions in the candidate action space to obtain target scores of the candidate actions, converting the target scores into action selection probabilities of the agent strategy network, and obtaining the target scores of the candidate actions. The action selection probability is used for driving an intelligent agent to perform action selection, and missing components of a tetrad in the time sequence knowledge graph are predicted based on a target entity searched by the intelligent agent, so that the space redundancy of the intelligent agent search action is remarkably reduced, the decision-making efficiency of the intelligent agent is improved, and the reasoning efficiency and accuracy of the time sequence knowledge graph are effectively improved.

The application provides a lung nodule benign and malignant fuzzy clustering method and system based on multi-dimensional feature modeling, an electronic device and a storage medium, and relates to the technical field of multi-dimensional feature modeling. The method comprises the following steps: acquiring multi-view refractive index data and low-dose CT images of a lung nodule region; extracting local texture features of the lung nodule region from the low-dose CT images, and fusing the multi-view refractive index data and the local texture features to generate fusion feature information; based on the fusion feature information, performing multi-angle polarized light field scanning on the lung nodule region to generate time-series light field data; based on the time-series light field data, generating a pulse sequence by using a pulse neural network; inputting an entropy value result of the pulse sequence into a preset fuzzy membership function, performing fuzzy clustering analysis by using the fuzzy membership function, and outputting a probability distribution result of lung nodule benign and malignant classification. The application improves the accuracy of benign and malignant differentiation of micro-lung nodules under low-dose CT.

This invention discloses a clustering-based method for determining the spatiotemporal layout of shared bicycles, belonging to the field of intelligent transportation technology. First, the invention systematically analyzes the current status of public bicycles to understand the characteristics of the existing system, and establishes buffer zones using ArcMap software. Second, it employs fuzzy C-means clustering analysis to cluster shared bicycle stations based on differences in daily usage time, obtaining the activity characteristics of various shared bicycle clusters. Finally, based on Points of Interest (POIs), a binary Logit model is used for regression analysis to obtain the locational characteristics of shared bicycle parking layouts. This invention provides an effective basis for travelers to make better travel decisions, and enables the rational allocation of public bicycle demand, thus improving the traffic environment.

The invention discloses a switched reluctance motor design optimization method and system based on a cooperative game theory, which converts a multi-objective optimization problem of switched reluctance motor design into a game problem, avoids subjectivity of manual weight setting, enables an optimization result to be more objective and reasonable, and improves the optimization efficiency. The game model can explicitly describe the cooperation potential or conflict degree between different targets instead of simple weighting or compromise, the mutual influence relation between the design targets is considered through the game model, a more comprehensive optimal solution can be obtained, the optimization result is prevented from deviating from the actual demand, and the optimization efficiency is improved. The strategy space of each gaming party is automatically determined through fuzzy clustering analysis, the optimization efficiency is improved, compared with a traditional multi-objective optimization method, the method is higher in convergence speed and fewer in iteration times, a multi-objective optimization function is represented by a revenue function, the most suitable strategy set is a to-be-solved motor size combination, and the optimization efficiency is improved. The optimized switched reluctance motor can balance the contradiction between the average electromagnetic torque and the electromagnetic vibration while keeping high efficiency.

The invention discloses a ground disaster monitoring and early warning method and system based on space-time weighted fuzzy clustering analysis. The method comprises the steps that A1, a monitoring device is installed; a2, collecting multi-source data through a monitoring device, and constructing a spatio-temporal data set; a3, key parameters in the multi-source data are extracted, and whether the key parameters exceed the limit or not is judged; if the limit is exceeded, an early warning is directly given out; if not, executing the step A4; step A4, preprocessing the multi-source data, including removing abnormal values, and performing normalization and space-time alignment processing; a5, analyzing and processing the data by adopting an improved fuzzy clustering algorithm, and recording a clustering category; and step A6, according to a clustering analysis result, judging whether an early warning notification is sent out or not. According to the scheme, the space-time weight matrix is introduced, the time correlation and the space dependence of the geological disaster monitoring data are effectively fused, the limitation that only data static characteristics are considered in a traditional clustering method is broken through, and the reliability of an analysis result is greatly improved.

The application discloses a kind of based on fuzzy C mean's district area electric vehicle charging behavior identification method and device, method includes the following steps: constructing the spatial data matrix and phase data matrix of electric vehicle charging;Set fuzzy value;With the initialization district area outgoing line load data fuzzy clustering center matrix and three-phase load data fuzzy clustering center matrix are constructed;Using fuzzy clustering analysis and through iterative calculation, determine optimal fuzzy clustering matrix and optimal fuzzy clustering center matrix;Obtain district area outgoing line load data fuzzy clustering center matrix optimal value and three-phase load data fuzzy clustering center matrix optimal value;Calculate the average value of district area outgoing line and three-phase load data power;According to power average value, identify three-phase electric vehicle charging power, confirm charging behavior.This method can identify district area electric vehicle charging behavior, determine the outgoing line and phase of electric vehicle in charging, provide theoretical guidance for district area operation management, charging station configuration, load prediction, control scheduling.

The invention provides a traditional Chinese medicine yin-yang disease identification method and system based on autonomous vegetative nerve parameters, and relates to the field of biological intelligence, and the method comprises the steps: collecting symptom feature information of the traditional Chinese medicine yin-yang disease and an identification data set corresponding to the symptom feature information of the traditional Chinese medicine yin-yang disease, the identification data set comprises index parameters of autonomous vegetative nerve change, and performing fuzzy clustering analysis on the same type of traditional Chinese medicine yin-yang disease parameters in the identification data set to obtain a common parameter subset corresponding to the same type of traditional Chinese medicine yin-yang diseases in the identification data set; training a maximum entropy model based on the common parameter subset to generate a disease cognition identification model corresponding to the parameter subset; and inputting a common parameter subset to be identified into the disease cognition identification model for matching so as to obtain disease information and a traditional Chinese medicine solution corresponding to the common parameter subset. According to the invention, the accuracy of disease identification can be improved.

The present invention discloses a vehicle intelligent battery swap navigation method and system based on a multi-objective genetic algorithm. The method includes: obtaining a power battery loss value and driver behavior data, and performing fuzzy cluster analysis on the driver behavior data; sending a battery swap warning message when the power battery loss value is greater than a preset value or the power battery SOC value is less than a first preset threshold; selecting and entering a battery swap navigation calculation mode, detecting the vehicle's instantaneous vehicle information, and calculating the remaining cruising range based on the SOC value; searching for multiple battery swap stations based on the instantaneous vehicle information and the remaining cruising range, and obtaining battery swap waiting data for each battery swap station and basic road data for the vehicle to each battery swap station, as well as driver behavior data after fuzzy cluster analysis; establishing a multi-objective optimization model to solve for the optimal battery swap station and the optimal path. By analyzing the driver behavior data, the present invention can formulate personalized and efficient battery swap paths and battery swap stations based on the driver's behavior habits.

The application provides a coastal wetland rearing recovery ecological effect multi-index quantitative evaluation method and system, belongs to the technical field of ecological restoration evaluation, and comprises the following steps: acquiring remote sensing, measurement, account book and GIS data of a sample plot to construct sample plot index standard data set; constructing an ecological restoration effect index system based on a pressure-state-response framework; calculating the weight of each index in the ecological restoration effect index system by using an analytic hierarchy process, an entropy weight method and a variation coefficient method, and taking the arithmetic mean of the obtained weights as the final combined weight of each index; constructing an ecological restoration effect index EREI by linear weighting according to the combined weight; and taking the EREI value of each sample plot as input, and dividing the sample plot into a restoration effect grade by using a fuzzy clustering analysis method, so that the problems of un-systematic index system, large subjective weighting deviation, poor grading method stability and limited sample plot data in the current ecological restoration effect evaluation of wetland rearing areas are solved.

The invention relates to an intuitionistic fuzzy clustering method for symbol type block data, which constructs an intuitionistic fuzzy membership by simultaneously considering the membership and hesitation of an object to a class, minimizes the distance between the object weighted by the intuitionistic fuzzy membership and the center of the class, and improves the clustering accuracy. And clustering division capable of solving uncertainty and fuzziness of block data to the greatest extent is obtained. According to the method, N groups of clustering partitions under N groups of random initial conditions are obtained based on an intuitionistic fuzzy clustering method oriented to symbol block data, the optimal initial condition corresponding to the optimal clustering partition is found by utilizing an evaluation index, and the N groups of initial conditions are updated by utilizing the optimal initial condition; n groups of clustering partitions and optimal initial conditions corresponding to the optimal clustering partition are obtained through continuous iteration, and the global optimal clustering partition is found. Compared with other algorithms of the same type, the performance is improved, good interpretability is achieved, and new requirements of current intelligent factory application can be well met.

The invention provides a pulmonary nodule benign and malignant fuzzy clustering method and system based on multi-dimensional feature modeling, electronic equipment and a storage medium, and relates to the technical field of multi-dimensional feature modeling, and the method comprises the steps: obtaining multi-view refractive index data and a low-dose CT image of a pulmonary nodule region; extracting local texture features of the pulmonary nodule region from the low-dose CT image, and fusing the multi-view refractive index data and the local texture features to generate fused feature information; based on the fused feature information, performing multi-angle polarized light field scanning on the pulmonary nodule region to generate time sequence light field data; generating a pulse sequence by using a pulse neural network based on the time sequence light field data; and inputting the entropy result of the pulse sequence into a preset fuzzy membership function, executing fuzzy clustering analysis through the fuzzy membership function, and outputting a probability distribution result of benign and malignant classification of pulmonary nodules. According to the method, the benign and malignant identification accuracy of the micro pulmonary nodules under the low-dose CT is improved.

The invention relates to a process optimization method and system for repairing pressure vessel steel through pulse current, and the method comprises the following steps: carrying out the processing of different pulse current parameters on damaged pressure vessel steel, and obtaining the performance changes before and after the processing; performing normalization processing on the data of different pulse current parameters and performance changes, and performing fuzzy clustering analysis on the processed data to obtain analyzed data; constructing a model by adopting an artificial neural network and principal component analysis, and calculating the processed data by adopting the model to obtain optimized parameters; and repairing the damaged pressure vessel steel according to the optimized parameters, and verifying a repairing result. According to the method, the clustering analysis method, the artificial neural network prediction model and the principal component analysis method are applied to the process of repairing the pressure vessel steel through the pulse current, the optimal pulse current repairing parameters are obtained, the time for repairing the pressure vessel steel through the pulse current is greatly shortened, and a new method is provided for intelligent screening of repairing process parameters.