The traditional motivation behind feature selection algorithms is to find the best subset of features for a task using one particular learning algorithm. Given the recent success of ensembles, however, we investigate the notion of ensemble feature selection in this paper. This task is harder than traditional feature selection in that one not only needs to find features germane to the learning t...

Pruning an ensemble of classifiers is one of the most significant and effective issues in ensemble method topic. This paper presents a new ensemble pruning method inspired by upward stochastic walking idea. Our proposed method incorporates simulated annealing algorithm and forward selection method for selecting models through the ensemble according to the probabilistic steps. Experimental compa...

We study continuum percolation on certain negatively dependent point processes on R. Specifically, we study the Ginibre ensemble and the planar Gaussian zero process, which are the two main natural models of translation invariant point processes on the plane exhibiting local repulsion. For the Ginibre ensemble, we establish the uniqueness of infinite cluster in the supercritical phase. For the ...

I present a cluster Monte Carlo algorithm that gives direct access to the interface free energy of Ising models. The basic idea is to simulate an ensemble that consists of both configurations with periodic and with antiperiodic boundary conditions. A cluster algorithm is provided that efficently updates this joint ensemble. The interface tension is obtained from the ratio of configurations with...

We propose a cluster ensemble method to map the corpus documents into the semantic space embedded in Wikipedia and group them using multiple types of feature space. A heterogeneous cluster ensemble is constructed with multiple types of relations i.e. document-term, documentconcept and document-category. A final clustering solution is obtained by exploiting associations between document pairs an...

The multiplicities of stars, and some other properties, were collected recently by Eggleton & Tokovinin, for the set of 4559 stars with Hipparcos magnitude brighter than 6.0 (4558 excluding the Sun). In this paper I give a numerical recipe for constructing, by a Monte Carlo technique, a theoretical ensemble of multiple stars that resembles the observed sample. Only multiplicities up to 8 are al...

Adaptive tree structured clustering (ATSC) is our proposed divisive hierarchical clustering method that recursively divides a data set into 2 subsets using self-organizing feature map (SOM). In each partition, the data set is quantized by SOM and the quantized data is divided using agglomerative hierarchical clustering. ATSC can divide data sets regardless of data size in feasible time. On the ...

Hierarchical clustering algorithms are widely used in many fields of investigation. They provide a hierarchy of partitions of the same dataset. However, in many practical problems, the selection of a representative level (partition) in the hierarchy is needed. The classical approach to do so is by using a cluster validity index to select the best partition according to the criterion imposed by ...

Bagging ensemble selection (BES) is a relatively new ensemble learning strategy. The strategy can be seen as an ensemble of the ensemble selection from libraries of models (ES) strategy. Previous experimental results on binary classification problems have shown that using random trees as base classifiers, BES-OOB (the most successful variant of BES) is competitive with (and in many cases, super...