SICEM: A Generation Approach of Band Combination for Hyperspectral Imagery Reconstitution Based on Space and Information Analyses.

A band selection algorithm named space and information comprehensive evaluation model (SICEM) is proposed in this paper, which reconstitutes the hyperspectral imagery by building an optimal subset to replace the original spectrum. SICEM reduces the dimensions while keeping the vital information of an image, and these are accomplished through two phases. Specifically, the improved fast density peaks clustering (I-FDPC) algorithm is employed to pick out the scattered bands in geometric space to generate a candidate set Uat first. Then, we conduct pruning in Uthrough iterative information analysis until the target set Ωis built. In this phase, we need to calculate comprehensive information score (CIS) for every member in Uafter assigning weights to the amount of information (AoI) and correlation. In each iteration, the band with highest score is selected into Ω, and the ones highly related to it will be removed out of Uvia a threshold. Compared with the four state-of-the-art unsupervised algorithms on real-world HSI datasets (IndianP and PaviaU), we find that SICEM has strong ability to form an optimal reduced-dimension combination with low correlation and rich information and it performs well in discrete band distribution, accuracy, consistency, and stability.

A Search Method for Optimal Band Combination of Hyperspectral Imagery Based on Two Layers Selection Strategy.

A band selection method based on two layers selection (TLS) strategy, which forms an optimal subset from all-bands set to reconstitute the original hyperspectral imagery (HSI) and aims to cost a fewer bands for better performances, is proposed in this paper. As its name implies, TLS picks out the bands with low correlation and a large amount of information into the target set to reach dimensionality reduction for HSI via two phases. Specifically, the fast density peaks clustering (FDPC) algorithm is used to select the most representative node in each cluster to build a candidate set at first. During the implementation, we normalize the local density and relative distance and utilize the dynamic cutoff distance to weaken the influence of density so that the selection is more likely to be carried out in scattered clusters than in high-density ones. After that, we conduct a further selection in the candidate set using mRMR strategy and comprehensive measurement of information (CMI), and the eventual winners will be selected into the target set. Compared with other six state-of-the-art unsupervised algorithms on three real-world HSI data sets, the results show that TLS can group the bands with lower correlation and richer information and has obvious advantages in indicators of overall accuracy (OA), average accuracy (AA), and Kappa coefficient.

Application of constraint-based methods in Staphylococcus aureus metabolic network.

With the remarkable advances in reconstruction of genome-scale metabolic networks, computational methods are increasingly important in investigation of these networks. Since they only need a few available kinetic parameters, constraint-based modeling methods have attracted so much attention in recent years. With the important aid by COBRA Toolbox, Staphylococcus aureus metabolic network (S. aureus_iSB619 model) which contains 619 genes, 571 metabolites and 640 metabolic reactions is studied in the present paper. We investigated (mainly under glucose minimal media condition) the optimal flux distributions, optimal growth rates, dynamic growth, robustness analysis (to PGK and MDH reactions), gene deletion and uniform random sampling (all allowed flux distributions) of the model. The study provided a constraint-based modeling framework of Staphylococcus aureus, and the results could be used in its metabolic engineering and industry microbial research.

Robustness in B. thuringiensis metabolic network.

The robustness of complex biological networks means that networks are in a position to maintain their functions despite external and internal perturbations. It is a key characteristic of biological networks and might play an important role in the evolutionary process of biological networks. The purpose of this paper is, by investigating the fundamental organizational principles such as the so-called "bow tie" structure, "scale-free" structure and modularity that underlie B. thuringiensis metabolic network, to analyze some simple robustness mechanisms of B. thuringiensis metabolic network with their underlying significance. Furthermore, the analyzing of robustness of well-known citric acid cycle in two typical bacteria is used to illustrate the underlying usefulness of robustness in biological networks.