No abstract

Commission VII, WG VII/3 KEY WORDS: Feature Selection, Hyperspectral, Genetic Algorithm, Supported Vector Machine ABSTRACT:The high-dimensional feature vectors of hyper spectral data often impose a high computational cost as well as the risk of "over fitting" when classification is performed. Therefore it is necessary to reduce the dimensionality through ways like feature selection. Currently, there are two kinds of feature selection methods: filter methods and wrapper methods. The form kind requires no feedback from classifiers and estimates the classification performance indirectly. The latter kind evaluates the "goodness" of selected feature subset directly based on the classification accuracy. Many experimental results have proved that the wrapper methods can yield better performance, although they have the disadvantage of high computational cost. In this paper, we present a Genetic Algorithm (GA) based wrapper method for classification of hyper spectral data using Support Vector Machine (SVM), a state-of-art classifier that has found success in a variety of areas. The genetic algorithm (GA), which seek to solve optimization problems using the methods of evolution, specifically survival of the fittest, was used to optimize both the feature subset, i.e. band subset, of hyper spectral data and SVM kernel parameters simultaneously. A special strategy was adopted to reduce computation cost caused by the high-dimensional feature vectors of hyper spectral data when the feature subset part of chromosome was designed. The GA-SVM method was realized using the ENVI/IDL language, and was then tested by applying to a HYPERION hyper spectral image. Comparison of the optimized results and the un-optimized results showed that the GA-SVM method could significantly reduce the computation cost while improving the classification accuracy. The number of bands used for classification was reduced from 198 to 13, while the classification accuracy increased from 88.81% to 92.51%. The optimized values of the two SVM kernel parameters were 95.0297 and 0.2021, respectively, which were different from the default values as used in the ENVI software. In conclusion, the proposed wrapper feature selection method GA-SVM can optimize feature subsets and SVM kernel parameters at the same time, therefore can be applied in feature selection of the hyper spectral data.

The doping of variable valence metal cations into CeO2 is beneficial for catalytic NO reduction by CO.

There are five distinct core structures in the lipopolysaccharides of Escherichia coli and at least two in Salmonella isolates, which vary principally in the outer core oligosaccharide. Six outer core glycosyltransferases, E. coli K-12 WaaG, WaaB, and WaaO and Salmonella typhimurium WaaI, WaaJ, and WaaK, were cloned, overexpressed, and purified. A novel substrate for WaaG was isolated from ΔwaaG E. coli overexpressing the lipid A phosphatase lpxE and the lipid A late acyltransferase lpxM. The action of lpxE and lpxM in the ΔwaaG background yielded heptose2-1-dephospho Kdo2-lipid A, a 1-dephosphorylated hexa-acylated lipid A with the inner core sugars that is easily isolated by organic extraction. Using this structurally defined acceptor and commercially available sugar nucleotides, each outer core glycosyltransferases was assayed in vitro. We show that WaaG and WaaB add a glucose and galactose sequentially to heptose2-1-dephospho Kdo2-lipid A. E. coli K-12 WaaO and S. typhimurium WaaI add a galactose to the WaaG/WaaB product but can also add a galactose to the WaaG product directly without the branched core sugar added by WaaB. Both WaaI and WaaO require divalent metal ions for optimal activity; however, WaaO, unlike WaaI, can add several glucose residues to its lipid acceptor. Using the product of WaaG, WaaB, and WaaI, we show that S. typhimurium WaaJ and WaaK transfer a glucose and N-acetylglucosamine, respectively, to yield the full outer core. This is the first demonstration of the in vitro assembly of the outer core of the lipopolysaccharide using defined lipid A-oligosaccharide acceptors and sugar donors.