We present a new hierarchical clustering criteria which can be applied to data set. This is done after generating an initial partition by using a Topological Self Organizing Map. This criteria contains two terms which take into account two di erent errors simultaneously: the square error of the entire clustering (as the Ward criteria) and the topological structure given by the Self Organizing M...

Text clustering has been recognized as an important component in data mining. Self-Organizing Map (SOM) based models have been found to have certain advantages for clustering sizeable text data. However, current existing approaches lack in providing an adaptive hierarchical structure within in a single model. This paper presents a new method of hierarchical text clustering based on combination ...

This paper presents a validation methodology in ascending hierarchical clustering. The objects in validation are clustering hierarchies, and simulation is used. Under certain conditions, this methodology allows us to evaluate the quality of hierarchical structures, its robustness and fiability, according to the data structure. The effect of the application of a given criterion on some kind of s...

We investigate the environments of quasars using a semi-analytic model which includes both galaxy and quasar formations based on a hierarchical clustering scenario. We assume that a supermassive black hole is formed and fueled by the accretion of cold gas during a major merger of galaxies. Our model can reproduce not only the general form of the galaxy luminosity functions in the local Universe...

In the image databases, there is often a need to organize the images automatically by their content. For the content-based organization of the images, clustering operations can be applied. We present a new, efficient method for the clustering of large image databases. The method is based on hierarchical clustering of the image database using grid. In this paper, the grid-based clustering method...

This paper presents a new method for solving the following problem: Given a polygonal model of some geometric object generate several more and more approximative representations of this object containing less and less polygons. The idea behind the method is that small detail in the model is represented by many spatially close points. A hierarchical clustering algorithm is used to generate a hie...

There exist a wide variety of distributions over trees with infinitely many nodes, including the nested Chinese restaurant process (Blei et al., 2004), the Dirichlet diffusion tree (Neal, 2003), and Kingman’s coalescent (Kingman, 1982). These models differ from the TSSBP in that data can only be associated with a leaf node, or equivalently a full path from root to leaf. We chose to base our clu...

Cognitive experiments involving visual and movement tasks have been intensively studied using functional magnetic resonance imaging (fMRI). A common paradigm of such experiments is that subjects are required to complete different tasks such as visual task or movement task simultaneously. A key problem with these studies is how to identify various cerebral networks, even then all of them were ac...

The analysis of the submm anisotropies that will be mapped by the forthcoming map and planck satellites requires careful foreground subtraction before measuring CMB fluctuations. Among these, the foreground due to IR/submm thermal radiation from dusty sources was poorly known until recent observational breakthroughs began unveiling the properties of these objects. We hereafter briefly review th...