657results about How to "Improve clustering effect" patented technology

The invention discloses a clustering method based on mobile object spatiotemporal information trajectory subsections. The clustering method based on mobile object spatiotemporal information trajectory subsections comprises the steps that the three attributes of time, speed and direction are introduced, and a similarity calculation formula of the time, speed and direction is provided for analyzing an internal structure and an external structure of a mobile object trajectory; firstly, according to the space density of the trajectory, the trajectory is divided into a plurality of trajectory subsections, then the similarities of the trajectory subsections are judged by calculating differences of the trajectory subjections on the space, time, speed and direction, finally, trajectory subsections in a non-significant cluster are deleted or are merged into adjacent significant clusters on the basis of a first cluster result, and therefore an overall moving rule is displayed on the clustering spatial form. According to the clustering method based on the mobile object spatiotemporal information trajectory subsections, the clustering result is improved, higher application value is provided, a space quadtree is adopted to conduct indexing on the trajectory subsections, clustering efficiency is greatly improved under the environment of a large-scale trajectory number set, and trajectories can be effectively clustered.

The invention discloses a semi-supervised multi-spectral remote sensing image segmentation method based on spectral clustering; the segmentation process includes that: (1) the characteristics inputted to the multi-spectral sensing image are extracted; (2) N points without labels and M points with labels are randomly and evenly sampled from a multi-spectral sensing image with S pixel points to form a set n which is the summation of N and M, wherein M points with labels are used for creating pairing limit information Must-link and Cannot-link sets; (3) the sampled point set is analyzed through semi-supervised spectral clustering to obtain the class labels of the n (n=N+M) points; (4) the sampled n (n=N+M) points are used as the training sample to classify the rest (S-N-M) points through nearest-neighbor rule, each pixel point is assigned with a class label according to the class of the pixel point and is used as the segmentation result of the inputted image. Compared with prior art, the invention has good image segmentation effect, strong operability, improves the classification accuracy, avoids searching the optimum parameters through repeated test, has small limit on image size and is better applicable to the segmentation of multi-class multi-spectral sensing images.

The invention discloses a multi-dimensional data management-oriented cloud computing query processing method, belonging to the field of database. The method comprises the following steps: 1, building a cloud computing platform which consists of a master node and multiple slave nodes, wherein the master node is used for sending queries; the slave nodes are used for storing multi-dimensional data objects, receiving queries and returning the query results to users; and the master node and the slave nodes are connected through Internet; 2, dividing all slave nodes into multiple clusters with an IDBC (information density based clustering) algorithm so that the slave nodes in the same cluster have similar data objects; 3, creating a quadtree-based multi-dimensional index for each slave node cluster, and organizing the quadtree-based multi-dimensional indexes in a CAN (content addressable network); and 4, performing query processing.

The invention discloses a power system load data identification and recovery method. Firstly, according to user historical load data, the number of clusters and initial cluster centers of sample data are determined on the basis of the hill climbing method; secondly, the final cluster center and the characteristic curve of the historical load data are obtained on the basis of the fuzzy C-means clustering algorithm; thirdly, each kind of load characteristic curve is processed, and the feasible region interval where normal data of the load curve is located is obtained; fourthly, according to correlation coefficients with the load characteristic curves, the category to which a to-be-tested load curve belongs is determined; finally, on the basis of the feasible region interval and the to-be-tested load curve whose category is judged, bad data of to-be-tested load data is identified and corrected. According to the method, the fuzzy C-means algorithm serves as the basis, the hill climbing function method is used, the number of clusters and the initial cluster centers are determined at the same time to improve clustering efficiency, and the initial cluster center determination problem and identification effect judgment randomness problem of bad data are solved.

The invention relates to a graph model based saliency target detection method. First, the method includes improving the clustering effect of an HAIC (Hexagon Arrangement Iteration Clustering) algorithm by using MRF overall potential energy minimization image smoothing; dynamically setting a threshold value so as to enable areas similar in color while communicating with each other in space to be divided into the same area by utilizing an improvement-based graph model for image division; combining areas with rich borders and improving excess division of image borders by using an attractor propagation clustering method. Second, the method includes optimizing a saliency graph by adopting a manifold ranking algorithm according to a manifold structure among super pixels so as to highlight the whole saliency area in the final saliency graph further.

The invention discloses a scholars name disambiguation method based on heterogeneous network embedding, which comprises the following steps of 1) setting a plurality of authors needing disambiguation,collecting all papers related to the authors needing disambiguation, and generating a paper relation heterogeneous network by utilizing the authors of the collected papers and semantic information ofthe papers; 2) according to the paper relation heterogeneous network, generating paths containing text information of neighbor nodes of paper nodes through a meta-path-based random walk strategy, andstoring the paths as a training corpus; 3) using Skip-gram to train the training corpus, and generating a paper representation vector corresponding to each paper; 4) for an author needing disambiguation in the step 1), obtaining a paper representation vector corresponding to the paper of the author from the obtained paper representation vector, and 5) clustering the paper representation vector obtained in the step 4) to obtain a plurality of clusters to realize disambiguation of the author name.

A method for grid-based data clustering comprises: creating a feature space having a plurality of cubes by a computer and showing the feature space by an interface of the computer, disposing a plurality of data stored in a database into the cubes, and then defining a plurality of the cubes as populated cubes; identifying whether the data within each of the populated cubes being evenly distributed or not to define each populated cube as a major cube or minor cube; combining border data of the minor cubes with the data in the major cubes; and designating all the data combined with each other as in the same cluster and recursively processing the above procedures to cluster all the data stored in the database.

The invention discloses an order batching method based on an improved K-Means algorithm, and the method is based on data mining. The method comprises the following steps: 1, conducting vectorization of a data set and obtaining an order set X; 2, obtaining a distance threshold T1 and a distance threshold T2 through a cross-validation method; 3, using a Canopy algorithm to obtain a cluster number K and a center point; 4, using the K and the center point obtained in the previous step and the improved K-Means algorithm to conduct clustering; and 5, after obtaining a final clustering result, sorting orders according to the average arrival time of the orders of each cluster, and obtaining a result of order batching. The method can accurately batch a large number of logistics orders, so that the efficiency of sorting operation is improved and the time taken for the sorting step is reduced.

The invention discloses a Chinese Web document online clustering method based on common substrings. As known to all, search engines are important in application of information searching and positioning with sharp increase of information on the internet. Web document clustering can automatically classify return results of the search engines according to different themes so as to assist users to reduce query range and fast position needed information. The Web document online clustering is characterized in that non-numerical and non-structured characteristics of Web documents are required to be met on the one hand, and clustering time is required to meet online search requirements of users on the other hand. According to the two characteristics, the invention provides the Chinese Web document online clustering method based on common substrings, and the method comprises steps as follows: (1) firstly, preprocessing the first n query results returned by the search engines so as to realize deleting and replacing operation of non-Chinese characters in the return results of the search engines, (2) extracting common substrings in the Web documents by utilizing GSA, (3) presenting a weighting calculation formula referring to TF*IDF according to the common substrings which are extracted and then building a document characteristic vector model, (4) computing pairwise similarity of the Web documents on the basis of the model to acquire a similarity matrix, (5) adopting an improved hierarchical clustering algorithm to achieve clustering of the Web documents on the basis of the matrix, and (6) executing clustering description and label extraction. The Chinese Web document online clustering method based on common substrings has obvious advantages on performance, clustering label generation and clustering time effects.

The invention discloses a drive behavior identification method based on an intelligent mobile terminal. The method includes the steps of S1, using the intelligent mobile terminal to collect and screenvehicle original state data which comprises the acceleration and angular speed information of three axes; S2, preprocessing vehicle original motion state data; S3, using a main component analysis method to acquire driving behavior comprehensive feature vectors from the preprocessed data; S4, using a k-means clustering algorithm to perform cluster partition on the driving behavior comprehensive feature vectors to obtain optimal clustering number; S5, using an FCM algorithm to cluster the driving behavior comprehensive feature vectors according to the optimal clustering number to obtain the deblurred final clustering result; S6, collecting real-time vehicle state data, and identifying the vehicle driving behaviors according to the final clustering result. By the method, refined driving behavior data clustering is achieved, and vehicle driving behavior features are effectively clustered into turning, speed changing and lane changing.

The invention discloses a building load forecasting method and device based on an improved IHCMAC (Hyperball Cerebellar Model Articulation Controller) neural network model. The method comprises the steps of: simulating the actual operation of a building to obtain building cold/heat load data and influencing factor data; determining input variables of the model according to the degree of correlation between the influencing factors and the building cold/heat load; clustering the input variables according to a particle swarm-K mean clustering algorithm to obtain values of L clustering centers, i.e., model node values, and defining a Gaussian kernel function for each node; and updating the weights of the nodes via a weight training algorithm to obtain a building load forecasting value of the model. The method has the advantages of fast convergence, high learning precision and strong generalization ability, and can provide a decision basis for energy-saving optimization control of a building system.

The utility model relates to a discovering algorithm with clustered cycling associated rule, based on a differing sequence method of time series vector. Firstly, in view of the drawback of the current discovering algorithm with cycling associated rule on the problem of dividing a plurality of time domains, an algorithm called CMDSA is proposed. The algorithm selects a time series vector which comprises a item supporting degree as the data character in time area to cluster; meanwhile, the clustering number is controlled by a DB principle to reach the best clustering result, so that each time area under the cycling associated rule can be identified more accurately and more useful cycling associated rules can be found compared with the current algorithm. Aiming at the fact that all the current algorithm of cycling associated rule are based on the Apriori algorithm and the efficiency is low, an algorithm of CFP-tree based on Fp tree is proposed. The algorithm of CFP-tree adopts cycling tailoring technique based on the condition FP tree to enhance the algorithm efficiency. Thus, the adoption of the discovering algorithm with cycling associated rule of CFP-tree is far better than the prior algorithm based on Apriori in the time and space efficiency.

The invention provides a color image segmentation algorithm based on histograms. The method includes the following steps that firstly, the color image RGB three-component histograms are counted and preprocessed respectively, so that the waveforms of the histograms are kept as smoother as possible; secondly, the histograms are searched for wave troughs through a wave crest and wave trough quick positioning algorithm, and the wave troughs serve as threshold values so that the histograms can be divided into multiple levels; thirdly, the divided histograms are combined again, a new histogram is established again, the histograms are searched for the wave troughs through the wave crest and wave trough quick positioning algorithm again, the histogram is divided into multiple levels, and then an initial clustering center is determined; finally, super-pixels are extracted by segmenting a color image in advance, segmentation areas serve as sample data, and the sample data are clustered in a fuzzy mode according to the determined clustering center. According to the color image segmentation algorithm, execution efficiency and clustering performance of a color image fuzzy clustering algorithm are effectively improved, and effectiveness of the algorithm is verified through running time and PRI indexes.

The invention discloses a dialogue short text clustering method based on form and semantic similarity. The form similarity adopts character string editing distance similarity, and the semantic similarity is based on HowNet and WordNet knowledge bases; weight values of the short text and words are introduced during the calculation of the short text similarity. The dialogue short text clustering method based on the form and semantic similarity solves the problems of certain irregular and input wrong noise information, synonyms and semantic gaps included in the dialogue short text to a certain extent, and consequently, relatively great improvement is realized in comparison with a word bag vector based clustering method.

The invention discloses a spacecraft defect detection method based on an LVQ-GMM algorithm and a multi-objective optimization segmentation algorithm. According to the spacecraft defect detection method based on LVQ-GMM and multi-objective optimization segmentation, column-direction search comparison is carried out through the maximum temperature point value in infrared thermal image sequence datato obtain a transformation column step length; meanwhile, the data is partitioned by utilizing the maximum temperature value in the transient thermal response curve; obtaining a transformation row step length of each data block; according to the method, sampling is carried out by using a transformation column step length and a transformation row step length to obtain a sampling data set composed of transient thermal response curves containing typical temperature changes, and a Gaussian mixture model corresponding to classification of the sampling data set is obtained by using an LVQ-GMM algorithm, so that the corresponding probability of the classification data set is obtained. And classifying each transient thermal response curve in the data set by using the probability, and reconstructing a defect image by using the classified typical thermal response curve. And constructing a double-layer multi-target optimized thermal image segmentation framework to realize accurate segmentation ofdefects.

An SVR antifriction bearing performance degradation prediction method based on a krill-herd algorithm belongs to the field of functional approximation rotating machinery prediction methods. The method comprises the following steps: firstly analyzing time domain, frequency domain and time-frequency domain feature indexes, and proposing a feature extraction method based on combination of CEEMD and wavelet packet half-soft threshold noise reduction to perform fault diagnosis of an antifriction bearing; performing comprehensive evaluation of the fault degradation feature of the antifriction bearing for multiple feature parameters, and proposing a method of combining the LLE nonlinear feature dimension reduction method with the fuzzy C mean value; and finally, introducing the basic theory of the support vector regression machine, and proposing the prediction model of multivariable support vector regression machine based on the krill herd algorithm, optimizing parameters of the SVR, and selecting the optimal C, [sigma] parameters. The method is advantaged by high prediction precision, short calculation time, and good feature value prediction effect after clustering. The degradation process of the antifriction bearing can be precisely predicted through the abovementioned three steps.

The invention discloses a text clustering method. The method comprises the steps of receiving a text clustering instruction sent by a user; pre-training a pre-determined initial language model by utilizing the to-be-clustered corpus to obtain a target language model; sequentially inputting each text in the to-be-clustered corpus into the target language model for feature extraction, obtaining a sentence vector of each text in the to-be-clustered corpus according to a model output result, and generating a to-be-clustered sentence vector set; and, by utilizing a preset clustering algorithm, clustering the to-be-clustered corpora based on the to-be-clustered sentence vector set to obtain sentence vectors corresponding to each category, and determining a clustering result of the to-be-clustered corpora. The invention further discloses an electronic device and a computer storage medium. By utilizing the method and the device, the text clustering accuracy and efficiency can be improved.

The invention belongs to the technical field of a semantic vector space model semantic core method, and particularly relates to a co-occurrence latent semantic vector space model semantic core method based on literature resource topic clustering. The method mainly solves the problems that an existing semantic vector space model semantic core method is high in semantic information extraction complexity, is insufficient in semantic information extraction, is high in model dimension, is high in complexity on the aspects of time and space when the existing semantic vector space model semantic core method is applied to a clustering algorithm and the like. The co-occurrence latent semantic vector space model semantic core method based on the literature resource topic clustering comprises the following steps that: 1) preprocessing literature data; 2) carrying out word frequency statistics on an extracted keyword for subsequently establishing a co-occurrence matrix to be used; 3) taking whether the keyword is in the presence in the literature or not as a weight to construct a vector space model shown by the literature; 4) constructing a co-occurrence latent semantic vector space model; 5) constructing a semantic core function; and 6) carrying out literature clustering.

The invention discloses a rolling bearing fault diagnosing method and equipment based on CEEMDAN and CFSFDP, belonging to the field of fault diagnosis of rotary machines. The method comprises the steps of acquiring vibration signals of a bearing in a normal state and different fault mode states so as to obtain sample points of the vibration signals of different states, decomposing by using CEEMDANto obtain time and frequency domains characteristics of bearing diagnosis and screening out bearing state representation parameters along with the time domain and frequency domain characteristics, dividing the representation parameters into training samples and a test samples, then using a table CFSFDP algorithm as a bearing fault diagnosis model, inputting the training samples into the bearing fault diagnosis model, clustering output results, obtaining clustering amount, clustering center points of each type, and state types corresponding to the clustering center points, and inspecting the trained diagnosis model by using test samples. The method and equipment can identify different bearing fault types and fault degrees accurately and effectively.