An embedded two-layer feature selection approach for microarray data analysis

Feature selection is an important technique in dealing with application problems with large number of variables and limited training samples, such as image processing, combinatorial chemistry, and microarray analysis. Commonly employed feature selection strategies can be divided into filter and wrapper. In this study, we propose an embedded two-layer feature selection approach to combining the advantages of filter and wrapper algorithms while avoiding their drawbacks. The hybrid algorithm, called GAEF (Genetic Algorithm with embedded filter), divides the feature selection process into two stages. In the first stage, Genetic Algorithm (GA) is employed to pre-select features while in the second stage a filter selector is used to further identify a small feature subset for accurate sample classification. Three benchmark microarray datasets are used to evaluate the proposed algorithm. The experimental results suggest that this embedded two-layer feature selection strategy is able to improve the stability of the selection results as well as the sample classification accuracy.

The effect of a rapid heating rate, mechanical vibration and surfactant chemistry on the structure-property relationships of epoxy/clay nanocomposites

The role of processing conditions and intercalant chemistry in montmorillonite clays on the dispersion, morphology and mechanical properties of two epoxy/clay nanocomposite systems was investigated in this paper. This work highlights the importance of employing complementary techniques (X-ray diffraction, small angle X-ray scattering, optical microscopy and transmission electron microscopy) to correlate nanomorphology to macroscale properties. Materials were prepared using an out of autoclave manufacturing process equipped to generate rapid heating rates and mechanical vibration. The results suggested that the quaternary ammonium surfactant on C30B clay reacted with the epoxy during cure, while the primary ammonium surfactant (I.30E) catalysed the polymerisation reaction. These effects led to important differences in nanocomposite clay morphologies. The use of mechanical vibration at 4 Hz prior to matrix gelation was found to facilitate clay dispersion and to reduce the area fraction of I.30E clay agglomerates in addition to increasing flexural strength by over 40%.

Computational chemistry for graphene-based energy applications: progress and challenges.

Research in graphene-based energy materials is a rapidly growing area. Many graphene-based energy applications involve interfacial processes. To enable advances in the design of these energy materials, such that their operation, economy, efficiency and durability is at least comparable with fossil-fuel based alternatives, connections between the molecular-scale structure and function of these interfaces are needed. While it is experimentally challenging to resolve this interfacial structure, molecular simulation and computational chemistry can help bridge these gaps. In this Review, we summarise recent progress in the application of computational chemistry to graphene-based materials for fuel cells, batteries, photovoltaics and supercapacitors. We also outline both the bright prospects and emerging challenges these techniques face for application to graphene-based energy materials in future.