55results about How to "Attribute reduction" patented technology

The invention relates to the field of wireless sensor networks and fault diagnosis, and discloses a method for carrying out fault diagnosis on wireless sensor networks. The method comprises the following steps: S1, carrying out online real-time acquisition on data measured by sensor nodes in a wireless sensor network; S2, detecting the fault of a single sensor node by using the space and time characteristics of the data; S3, detecting the fault of the whole wireless sensor network by using the correlation between two adjacent nodes; S4, carrying out attribute reduction on parameters obtained in the steps S2 and S3; and S5, obtaining a fault diagnosis result of the wireless sensor network according to the attribute reduction result obtained in the step S4. In the invention, the fault of a single sensor node is detected by using the space and time characteristics of data measured by sensor nodes in a wireless sensor network, and the rapid and correct fault detection on all nodes in the network by using the correlation between the nodes is realized.

The invention discloses a method and a device for mining an association rule based on attribute reduction. The method comprises the following steps of S1, according to a studying object, collecting corresponding data from a database; S2, performing integration reduction on the data; S3, performing attribute reduction on the data after integration reduction by a rough set theory; S4, mining the association rule on the data after attribute reduction by an improved HEclat algorithm; S5, interpreting and showing the mined association rule. The method has the advantages that the attribute reduction is performed by the rough set theory during data processing, so as to avoid using a large amount of unnecessary attributes for interaction operation and increasing the computing of data quantity; in the data mining process, the data mining of the association rule is performed by the improved HEclat algorithm, and the database is only scanned at one time, so that the redundancy computing is reduced, the data mining time is effectively shortened, the consumption of system resources is reduced, and the data mining efficiency is improved.

The invention relates to an on-line service credit measurement method based on multi-dimensional evaluation information, and belongs to the technical field of on-line credit measurement. Firstly, principal component analysis of multi-dimensional attribute information of the online service credit is carried out; the attribute dimension which affects the dynamic change of the online service credit is selected; and the evaluation data of online service attributes is screened with consideration of time factors; secondly, a service credit labeling criterion is established, and then an initial sample is labeled and a support vector machine classification model is trained; a training sample is obtained through a self-learning method of distance correlation; a training sample set and a SVM classification model are updated; and finally, the finally updated SVM classification model is used to determine the credit labels of the online service to realize service credit measurement. According to the invention, through taking regard of the multiple dimensions and time factors of the credit attributes, the service credit is made to change with new transaction. In addition, a support vector machine can effectively deal with the problem of the excessive calculating complexity brought about by a high data dimension.

The invention discloses an attribute reduction method for an information system based on MPI parallel solving. The attribute reduction method comprises the following steps: firstly, reading the data of the information system, pretreating numerical values, and carrying out data discretization; then, horizontally dividing the information system into p sample data subsets, assigning to n nodes through communication, calculating the equivalence class of the data subsets in parallel, and integrating the result of each node to obtain m equivalence class division information subsystems of the whole information system; then, assigning the m information subsystems to the n nodes, carrying out parallel attribute core computing until all the information subsystems are processed, then merging the results of the nodes to obtain the attribute core of the whole information system; and finally, carrying out parallel solving attribute reduction, and merging the attribute reduction results of the nodes to obtain the attribute reduction of the whole information system. A rough set attribute reduction method is combined with MPI parallel computing, so that parallel solving can be carried out by using differentiation matrix solving attribute reduction calculation, and the algorithmic efficiency is improved.

The invention relates to a relay individual working life predicting and screening method based on early life performance. The relay individual working life predicting and screening method based on early life performance is characterized by comprising the following steps that under an environment temperature C1, the performance parameters C ={C2,C3, ...,Cn} and the working life D of a relay sample at the early life are acquired according to the service life test of the relay sample; a relay individual working service decision table is established based on a rough set theory and an equal probability criterion by using the C as condition attributes and using the D as decision attributes; a set of association rules with respect to the early life performance and the service life of relay individuals are extracted by the aid of attribute reduction; afterwards, for the individuals of the same specifications, the service life of the individuals can be predicted by only measuring the performance parameters of the individuals at the early life, and therefore relays can be screened. According to the method, when the working life of the relay individuals are predicted and products are screened, only the early life performance of the relay individuals is needed, no more information is needed, the time and cost for acquiring information are greatly saved, the calculation is small, and the effective service life of the relays can also not excessively shortened.

The invention relates to the technical field of equipment test identification. The invention discloses a method for constructing an equipment combat test identification index system. The method is anequipment combat test identification index optimization method based on a rough set and a genetic algorithm and comprises the steps that (1) a basic framework of an equipment combat test index systemis constructed; (2) a decision information table is constructed, the concept of the decision information system is derived from a rough set method, and definition is given to the rough set and the decision information system; (3) the attribute reduction method based on the genetic algorithm comprises the following steps: a) chromosome coding, b) fitness function, c) roulette strategy selection operation, d) crossover operation,..; and (4) a simplified index set is obtained to obtain an attribute reduction set of the equipment decision information system. Through the rough set and the genetic algorithm method, various uncertain information can be well processed, qualitative and quantitative information is analyzed and mined, attributes of the information are reduced, and a simplified indexset is obtained; intelligent evaluation is achieved, and the method is simple, visual and good in effect.

The invention discloses an attribute alignment method and apparatus, relates to the field of data analysis, and aims to solve the problem of high calculation complexity caused by matching between an attribute of a data source and multiple attributes of another data source. The attribute alignment method comprises the steps of obtaining N data sources; according to the N data sources, obtaining anattribute name set and generating an internal dictionary; according to the attribute name set, the internal dictionary and an attribute name of each data source in the N data sources, obtaining an attribute eigenvector of each data source; according to the attribute eigenvector of each data source, calculating the similarity between any two data sources in the N data sources and a similarity matrix; according to the similarity matrix, clustering the N data sources to obtain k clusters; and according to the internal dictionary, performing attribute alignment on the data sources of the same cluster in the k clusters to obtain k data sources, and performing attribute alignment on the k data sources to obtain a result data resource. The attribute alignment method and apparatus is applied to the data analysis.

The invention relates to the technical field of network communication structures, in particular to a routing system related to network topology based on graphic configuration database businesses. The routing system is sent by a source and provides one or multiple destinations for use, wherein access and mobility requirements of a network node are involved. The routing system is characterized in that the network node comprises a service module graphic configuration database, one or multiple node transmission networks operate on a host which is used for reflecting object program functions for routes used under requests of the service module graphic configuration database of each service, and as for given services, the service module graphic configuration database is connected with a conventional relational database service module CMDB (configuration management database). Compared with the prior art, the routing system related to the network topology based on the graphic configuration database businesses has the advantages that the routing system is more accordant with thinking habits of people, convenient to operate, remarkably improved in performance and quick in operation speed, and provides an effective technical measure for analyzing business influences and handling business faults.

The invention provides an intelligent screening method for critical indexes of predicting fatal gastrointestinal rebleeding in a hospital, and the method comprises the following steps: extracting index data of a patient suffering from gastrointestinal hemorrhage from a database according to an inclusion exclusion standard, and calculating an outcome identifier; performing data cleaning on the index data to process abnormal values, and removing redundant indexes and indexes of which missing values are serious and cannot be analyzed; discretizing the index data according to a discretization standard set according to a clinical actual situation; taking the discretized index data as a condition attribute, and taking an outcome identifier as a decision attribute; inputting the condition attributes and the decision attributes into a screening algorithm model, calculating fitness, iteratively repeating until the fitness is not increased any more and the indexes are not reduced any more, and obtaining screened key index data. The method can efficiently and stably calculate the key index for indicating that the patient suffering from gastrointestinal hemorrhage suffers from hospital fatal rebleeding, and assists a doctor in making a decision.

The invention discloses a segmented prediction method and device for silicon content of melted iron of a blast furnace. The method comprises the steps of 1, obtaining historical smelting data of the blast furnace as sample data, wherein the sample data includes condition attribute data and a decision value, and the decision value is the silicon content; 2, creating a segmented decision table whichincludes a regular decision table, a high silicon decision table and a low silicon decision table; 3, conducting attribute reduction on the segmented decision table to obtain a segmented knowledge base which includes a conventional knowledge base, a high silicon knowledge base and a low silicon knowledge base, and restoring decision values in all the knowledge bases to original data; 4, searchingfor the knowledge base matched with a sample to be measured, and obtaining a sample matched with the sample to be measured; 5, calculating the prediction value of the silicon content according to thedecision value of the sample matched with the sample to be measured in the matched knowledge base. By means of the method, the accuracy of the prediction value of the silicon content is improved.

The invention discloses a rough set theory-based civil aviation radio interference prediction method. The method comprises the following steps of: firstly carrying out attribute classification on civil aviation radio interference report data, extracting attributes associated with an interfered process, determining a condition attribute set and a decision attribute, and establishing an interference data decision table; carrying out data pre-processing on each attribute value contained in the interface data decision table, and carrying out attribute reduction and attribute value reduction on the pre-processing result by adoption of a special reduction method which is designed on the basis of a database, thereby obtaining an interference decision rule table; and finally solving an influence degree table indicating influences, on the decision attribute, of a condition attribute value by utilizing a credibility function, and carrying out operation state diagnosis on the interference report data by utilizing the decision rule table and the influence degree table, thereby obtaining interference pre-warning values of regions contained in the data. The accuracy degree of the prediction result of the method is higher than the accuracy degree of the prediction result of a time series-based prediction method; and the method is independent of assumed conditions and has no requirements for accurate data.

The invention provides a method and a system for controlling a chip die bonder. The method comprises the steps of: acquiring the image of a motion platform, and the image includes the information of a wafer; determining the position relationship between the wafer on the motion platform and an operated object according to the image; controlling the movement of an end effector according to the acquired position relationship, so that the wafer on the motion platform moves to a target position; controlling the end effector for die bond. The method and the system control the die bonder in a vision-guided mode; therefore, the positioning effect is good, and the problems of the jitter of mechanical platform motion and the overall deviation of the positioning location can be resolved.

The directionally searching backward coarse set attribute reducing method adopts mutual information and redundant cooperation index of the attribute subset as the measurement of the reducing coarse set attribute. The initial attribute sets are first sorted and several equivalent attribute subsets with minimum redundant cooperation index are selected from the subsets of the initial attribute sets and are stored in the directional memory area; several next level equivalent attribute subsets with minimum redundant cooperation index are then selected from the next level subsets of equivalent attribute subsets for further search; and so on until no further equivalent attribute subset can be found. The attribute subsets ultimately stored in the directional memory area are the attribute reducing result. The said method is flexible, simple and universal, and may be used in all coarse set attribute reducing fields.

The invention discloses an automatic medical image processing system. Through close combination of image data mining theoretical research and practical application, the mainstream technology of current medical image data mining is discussed. The method is based on improvement of a statistical learning theory, a decision tree classification algorithm, an association rule algorithm and a rough set decision tree algorithm. According to the association rule classification method, the problems existing in association rule classification are solved, formats of multi-source medical equipment data arepackaged, a unified processing interface is adopted to form a normalized data directory, redundant features are removed, attribute reduction is carried out, the classification efficiency is improved,and the processing time is shortened. According to the construction of the medical knowledge graph, a key technology can be applied to computer-aided diagnosis, and a medical image automatic processing system based on an image data mining technology is constructed.

The embodiment of the invention provides a cross-media emotion correlation method and system. The method comprises the steps of playing a group of images by an intelligent TV, extracting the underlying visual characteristic set of the group of images, sending the extracted underlying visual characteristic set to a server, conducting the attribute reduction on the underlying visual characteristic set, inputting the attribute-reduced underlying visual characteristic set to a pre-trained emotion model to obtain the emotion type of the group of images, further determining an emotion characteristic vector corresponding to the attribute-reduced underlying visual characteristic set of the group of images by the server based on the emotion model and the obtained emotion type, figuring out an audio file associated with the emotion of the above group of images in an audio database by the server based on the determined emotion characteristic vector, returning the audio file to the intelligent TV, and playing the group of images together with the associated audio file by the intelligent TV. By means of the above method and the above system, when a user views images by the intelligent TV, the intelligent TV automatically plays the audio file that is adapted to the images in artistic conception. Therefore, the user experience is improved.

The invention discloses a medical automatic image processing system. The image data mining theoretical research is tightly combined with the practical application, and the mainstream technology of current medical image data mining is discussed; the method is based on improvement of a statistical learning theory, a decision tree classification algorithm, an association rule algorithm and a rough set decision tree algorithm. The invention further discloses an association rule classification method, so problems existing in association rule classification are solved; the format of the multi-sourcemedical equipment data is packaged, and a unified processing interface is adopted to form a normalized data directory, so the classifying efficiency is improved and the processing time is reduced; meanwhile, the key technology can be applied to computer-aided diagnosis through the construction of the medical knowledge graph, and the medical automatic image processing system based on the image data mining technology is constructed.

The invention relates to a polycrystalline silicon ingot casting quality prediction method and system based on batching data. The method comprises the following steps: acquiring batching data of a polycrystalline silicon ingot; preprocessing the batching data; wherein the preprocessing comprises the steps of performing data cleaning and deleting data with missing numerical values; performing dimension reduction processing on the preprocessed batching data by using a diffusion mapping algorithm; constructing a support vector data description model by using the batching data subjected to dimension reduction processing in a set proportion; and utilizing the trained support vector data description model to carry out quality prediction classification on the batching data after dimension reduction processing to obtain a product quality prediction classification result. According to the polycrystalline silicon ingot casting quality prediction method and system based on the burdening data, prediction of the polycrystalline silicon ingot casting quality can be rapidly and accurately achieved with low cost.

The embodiment of the invention discloses an abnormal behavior recognition and risk model library establishment method and device and electronic equipment, and is used for solving the problem that an existing abnormal behavior recognition method is not accurate enough. The method comprises the following steps: collecting multiple groups of abnormal behavior feature data of a risk scene and corresponding abnormal classification tags; discretizing the multiple groups of abnormal behavior feature data to obtain risk feature values corresponding to multiple parts of abnormal behavior feature data in the multiple groups of abnormal behavior feature data; carrying out attribute reduction on risk feature categories corresponding to a plurality of abnormal behavior feature data in the plurality of groups of abnormal behavior feature data; and establishing a risk model library based on a relationship among the risk feature category set after attribute reduction, the risk feature values and the corresponding abnormal classification tags.