Towards improving cluster-based feature selection with a simplified silhouette filter

This paper proposes a filter-based algorithm for feature selection. The filter is based on the partitioning of the set of features into clusters. The number of clusters, and consequently the cardinality of the subset of selected features, is automatically estimated from data. The computational complexity of the proposed algorithm is also investigated. A variant of this filter that considers feature-class correlations is also proposed for classification problems. Empirical results involving ten datasets illustrate the performance of the developed algorithm, which in general has obtained competitive results in terms of classification accuracy when compared to state of the art algorithms that find clusters of features. We show that, if computational efficiency is an important issue, then the proposed filter May be preferred over their counterparts, thus becoming eligible to join a pool of feature selection algorithms to be used in practice. As an additional contribution of this work, a theoretical framework is used to formally analyze some properties of feature selection methods that rely on finding clusters of features. (C) 2011 Elsevier Inc. All rights reserved.

A PRELIMINARY ANALYSIS OF THE ENERGY TRANSFER BETWEEN THE DARK SECTORS OF THE UNIVERSE

We study the mutual interaction between the dark sectors (dark matter and dark energy) of the Universe by resorting to the extended thermodynamics of irreversible processes and constrain the former with supernova type Ia data. As a by-product, the present dark matter temperature results are not extremely small and can meet the independent estimate of the temperature of the gas of sterile neutrinos.

Magnetic Susceptibility Measurements at Ultra-low Temperatures

We report the design and operation of a device for ac magnetic susceptibility measurements that can operate down to 1 mK. The device, a modification of the standard mutual inductance bridge, is designed with detailed consideration of the thermalization and optimization of each element. First, in order to reduce local heating, the primary coil is made with superconducting wire. Second, a low-temperature transformer which is thermally anchored to the mixing chamber of a dilution refrigerator, is used to match the output of the secondary coil to a high-sensitivity bridge detector. The careful thermal anchoring of the secondary coil and the matching transformer is required to reduce the overall noise temperature and maximize sensitivity. The sample is immersed in liquid (3)He to minimize the Kapitza thermal resistance. The magnetic susceptibility of several magnetic compounds, such as the well-known spin gap compound NiCl(2)-4SC(NH(2))(2) and other powdered samples, have been successfully measured to temperatures well below 10 mK.