
PARAMETER-FREE CLUSTER DETECTION IN SPATIAL
... The first basic step is the computation of the Delaunay Triangulation (DT) from a given set of points. In the next step we compute first the Gabriel Graph (GG) from the DT, second the Relative Neighborhood Graph (RNG) from the GG, and third the Nearest Neighbor Graph (NNG) from the RNG (figure 1a)). ...
... The first basic step is the computation of the Delaunay Triangulation (DT) from a given set of points. In the next step we compute first the Gabriel Graph (GG) from the DT, second the Relative Neighborhood Graph (RNG) from the GG, and third the Nearest Neighbor Graph (NNG) from the RNG (figure 1a)). ...
Region Discovery Technology - Department of Computer Science
... interested to have similar capabilities to find interesting regions on the planet earth based on knowledge that s stored in multiple databases. The Data Mining and Machine Learning Group of the University of Houston (UH-DMML) centers on developing technologies that can satisfy this very need. The fo ...
... interested to have similar capabilities to find interesting regions on the planet earth based on knowledge that s stored in multiple databases. The Data Mining and Machine Learning Group of the University of Houston (UH-DMML) centers on developing technologies that can satisfy this very need. The fo ...
Review of Kohonen-SOM and K-Means data mining Clustering
... Clustering is one of the primary tasks used in the pattern recognition and data mining communities to search VL databases (including VL images) in various applications, and so, clustering algorithms that scale well to VL data are important and useful. This article compares the efficacy of three diff ...
... Clustering is one of the primary tasks used in the pattern recognition and data mining communities to search VL databases (including VL images) in various applications, and so, clustering algorithms that scale well to VL data are important and useful. This article compares the efficacy of three diff ...
Comparative Study on Hierarchical and Partitioning Data Mining
... Ease of handling of any forms of similarity or distance Consequently, applicability to any attributes types. ...
... Ease of handling of any forms of similarity or distance Consequently, applicability to any attributes types. ...
K-Means and K-Medoids Data Mining Algorithms
... often referred as, is a data mining activity that aims to differentiate groups (classes or clusters) inside a given set of objects , being considered the most important unsupervised learning problem. The resulting subsets or groups, distinct and non-empty, are to be built so that the objects within ...
... often referred as, is a data mining activity that aims to differentiate groups (classes or clusters) inside a given set of objects , being considered the most important unsupervised learning problem. The resulting subsets or groups, distinct and non-empty, are to be built so that the objects within ...
Data Clustering Method for Very Large Databases using entropy
... the clusters they were put in. We proceed to remove these points from their clusters and re-cluster them. The way we figure out how good a fit a point is for the cluster where it landed originally, is by keeping track of the number of occurrences of each of its attributes' values in that cluster. Th ...
... the clusters they were put in. We proceed to remove these points from their clusters and re-cluster them. The way we figure out how good a fit a point is for the cluster where it landed originally, is by keeping track of the number of occurrences of each of its attributes' values in that cluster. Th ...
Clustering I - CIS @ Temple University
... • Use distance matrix as clustering criteria. This method does not require the number of clusters k as an input, but needs a termination condition Step 0 ...
... • Use distance matrix as clustering criteria. This method does not require the number of clusters k as an input, but needs a termination condition Step 0 ...
Implementation and Evaluation of K-Means, KOHONEN
... trained using unsupervised learning to produce a low-dimensional (typically two dimensional), discretized representation of the input space of the training samples, called a map. Self-organizing maps are different than other artificial neural networks in the sense that they use a neighborhood functi ...
... trained using unsupervised learning to produce a low-dimensional (typically two dimensional), discretized representation of the input space of the training samples, called a map. Self-organizing maps are different than other artificial neural networks in the sense that they use a neighborhood functi ...
Nearest-neighbor chain algorithm

In the theory of cluster analysis, the nearest-neighbor chain algorithm is a method that can be used to perform several types of agglomerative hierarchical clustering, using an amount of memory that is linear in the number of points to be clustered and an amount of time linear in the number of distinct distances between pairs of points. The main idea of the algorithm is to find pairs of clusters to merge by following paths in the nearest neighbor graph of the clusters until the paths terminate in pairs of mutual nearest neighbors. The algorithm was developed and implemented in 1982 by J. P. Benzécri and J. Juan, based on earlier methods that constructed hierarchical clusterings using mutual nearest neighbor pairs without taking advantage of nearest neighbor chains.