Growing Neural Gas approach for obtaining homogeneous maps by restricting the insertion of new nodes

The Growing Neural Gas model is used widely in artificial neural networks. However, its application is limited in some contexts by the proliferation of nodes in dense areas of the input space. In this study, we introduce some modifications to address this problem by imposing three restrictions on the insertion of new nodes. Each restriction aims to maintain the homogeneous values of selected criteria. One criterion is related to the square error of classification and an alternative approach is proposed for avoiding additional computational costs. Three parameters are added that allow the regulation of the restriction criteria. The resulting algorithm allows models to be obtained that suit specific needs by specifying meaningful parameters.

Enhancement of the Electrochemical Performance of SWCNT dispersed in a Silica Sol-gel Matrix by Reactive Insertion of a Conducting Polymer

The electroassisted encapsulation of Single-Walled Carbon Nanotubes was performed into silica matrices (SWCNT@SiO2). This material was used as the host for the potentiostatic growth of polyaniline (PANI) to yield a hybrid nanocomposite electrode, which was then characterized by both electrochemical and imaging techniques. The electrochemical properties of the SWCNT@SiO2-PANI composite material were tested against inorganic (Fe3+/Fe2+) and organic (dopamine) redox probes. It was observed that the electron transfer constants for the electrochemical reactions increased significantly when a dispersion of either SWCNT or PANI was carried out inside of the SiO2 matrix. However, the best results were obtained when polyaniline was grown through the pores of the SWCNT@SiO2 material. The enhanced reversibility of the redox reactions was ascribed to the synergy between the two electrocatalytic components (SWCNTs and PANI) of the composite material.