GPU implementation of Jacobi method for data arrays that exceed
... videomemory size limits the dimension of problems that GPU might solve. However as the Eq. 3 is almost identical to the iteration of a regular explicit finite-difference method for a non-stationary heat equation, the previously used pyramid method may also be used for this iteration [5]. This method ...
... videomemory size limits the dimension of problems that GPU might solve. However as the Eq. 3 is almost identical to the iteration of a regular explicit finite-difference method for a non-stationary heat equation, the previously used pyramid method may also be used for this iteration [5]. This method ...
Data Mining Cluster Analysis: Basic Concepts and Algorithms L t N
... – A cluster is a dense region of points, which is separated by low-density regions, from other regions of high density. – Used when the clusters are irregular or intertwined, and when noise and outliers are present. ...
... – A cluster is a dense region of points, which is separated by low-density regions, from other regions of high density. – Used when the clusters are irregular or intertwined, and when noise and outliers are present. ...
A Lattice Algorithm for Data Mining
... attributes [FU 03a, RIO 03]. We propose a new definition: dual algorithm, which consists of applying an algorithm to the same context by inverting rows and columns. The duality of lattice algorithm is considered in our comparison of lattice algorithms. The difference between algorithm and its dual a ...
... attributes [FU 03a, RIO 03]. We propose a new definition: dual algorithm, which consists of applying an algorithm to the same context by inverting rows and columns. The duality of lattice algorithm is considered in our comparison of lattice algorithms. The difference between algorithm and its dual a ...
Document
... accuracy of trained classifiers on specific datasets. If we have enough data, We can sample a number of training sets of size N, run the two learning algorithms on each of them, and then estimate the difference in accuracy for each pair of classifiers on a large test set. The average of these differ ...
... accuracy of trained classifiers on specific datasets. If we have enough data, We can sample a number of training sets of size N, run the two learning algorithms on each of them, and then estimate the difference in accuracy for each pair of classifiers on a large test set. The average of these differ ...
77. diffused kernel dmmi approach for theoretic clustering using data
... These challenges led to the emergence of applicable data mining clustering methods. K-Means based Clustering Algorithm One of the most common iterative algorithms is the K-means algorithm [2], [10], [15] broadly used for its simplicity of implementation and convergence speed. K-mean algorithm crea ...
... These challenges led to the emergence of applicable data mining clustering methods. K-Means based Clustering Algorithm One of the most common iterative algorithms is the K-means algorithm [2], [10], [15] broadly used for its simplicity of implementation and convergence speed. K-mean algorithm crea ...
A Multiobjective Genetic Algorithm for Attribute Selection
... At each generation, selection is performed as follows. First the GA selects all the non-dominated individuals (the Pareto front) of the current population. These non-dominated individuals are passed unaltered to the next generation by elitism [1]. Let N be the population size, and let Nelit be the n ...
... At each generation, selection is performed as follows. First the GA selects all the non-dominated individuals (the Pareto front) of the current population. These non-dominated individuals are passed unaltered to the next generation by elitism [1]. Let N be the population size, and let Nelit be the n ...
Mining Association Rules Based on Certainty
... frequent item sets with the size 2. At this time, the algorithm found out the frequent item sets by the formula in order to obtain the enhanced association rules. The reason why the algorithm produced the k-item sets after scanning the database one time is that it can reduce the computational comple ...
... frequent item sets with the size 2. At this time, the algorithm found out the frequent item sets by the formula in order to obtain the enhanced association rules. The reason why the algorithm produced the k-item sets after scanning the database one time is that it can reduce the computational comple ...
Agent and Data Mining - University of Technology Sydney
... Agents as a new computing paradigm for complex problems • Strengths – Analyze and understand complex systems – Deal with nonfunctional requirements – Handle social complexity such as distribution, dynamics, interaction, evolution, self-organization – Build flexible infrastructure ...
... Agents as a new computing paradigm for complex problems • Strengths – Analyze and understand complex systems – Deal with nonfunctional requirements – Handle social complexity such as distribution, dynamics, interaction, evolution, self-organization – Build flexible infrastructure ...
Conceptual Clustering Categorical Data with Uncertainty
... paradigm for clustering. It is different than other clustering algorithms in that it generates a concept descriptor for each cluster. COBWEB [DHFisher87] is one of the mostly commonly used algorithms for conceptual clustering. In this paper, we extend the COBWEB algorithm for clustering data with un ...
... paradigm for clustering. It is different than other clustering algorithms in that it generates a concept descriptor for each cluster. COBWEB [DHFisher87] is one of the mostly commonly used algorithms for conceptual clustering. In this paper, we extend the COBWEB algorithm for clustering data with un ...
Complex building`s energy system operation patterns analysis using
... par rapport the method of bag of patterns using hierarchical clustering. The authors have concluded that the bag of patterns representation (BoPR) approach performed better for finding similarities in the time series data as compared to other methods. The use of bag of words model can be seen in var ...
... par rapport the method of bag of patterns using hierarchical clustering. The authors have concluded that the bag of patterns representation (BoPR) approach performed better for finding similarities in the time series data as compared to other methods. The use of bag of words model can be seen in var ...
Conceptual Clustering Categorical Data with Uncertainty
... methods, such as STING, quantize the space into finite number of cells to form a grid structure, on which all of the operations for clustering are performed. Conceptual clustering produces a classification scheme over the objects, and it goes one step further than other clustering algorithms by find ...
... methods, such as STING, quantize the space into finite number of cells to form a grid structure, on which all of the operations for clustering are performed. Conceptual clustering produces a classification scheme over the objects, and it goes one step further than other clustering algorithms by find ...
Classification Models Based-on Incremental Learning Algorithm and Feature Selection on
... 3. 4 An Incremental Learning Algorithm based on Mahalanobis Distance (ILM) The objective of ILM is incremental learning, covering supervised and unsupervised learning, hard and soft decisions [3] [20], Mahalanobis distance measurement, and Gaussian function [3]. ILM contains two steps: learning step ...
... 3. 4 An Incremental Learning Algorithm based on Mahalanobis Distance (ILM) The objective of ILM is incremental learning, covering supervised and unsupervised learning, hard and soft decisions [3] [20], Mahalanobis distance measurement, and Gaussian function [3]. ILM contains two steps: learning step ...
Document
... Discovery of new types of galaxies in astronomical data Clustering of genes with similar expression profiles Cluster pixels in an image into regions of similar intensity Segmentation of customers for an e-commerce store Clustering of documents produced by a search engine ...
... Discovery of new types of galaxies in astronomical data Clustering of genes with similar expression profiles Cluster pixels in an image into regions of similar intensity Segmentation of customers for an e-commerce store Clustering of documents produced by a search engine ...
Shallow Text Clustering Does Not Mean Weak Topics - CEUR
... extension) and the task of topic identification (extracting within-category commonalities, their intension), as highlighted by [26]. We show here that not-so-good (shallow) clustering does not always mean weak topics. Another observation is related to the vocabulary used by the algorithms: most of t ...
... extension) and the task of topic identification (extracting within-category commonalities, their intension), as highlighted by [26]. We show here that not-so-good (shallow) clustering does not always mean weak topics. Another observation is related to the vocabulary used by the algorithms: most of t ...
A Classification Technique using Associative
... learning), Predictive modeling (also called classification or supervised learning), and Frequent pattern extraction. Clustering is the major class of data mining algorithms. The goal of the search process used by these algorithms is to identify all sets of similar examples in the data, in some optim ...
... learning), Predictive modeling (also called classification or supervised learning), and Frequent pattern extraction. Clustering is the major class of data mining algorithms. The goal of the search process used by these algorithms is to identify all sets of similar examples in the data, in some optim ...
