Decision tree classification of land cover from remotely sensed data

Decision tree classification algorithms have significant potential for land cover mapping problems and have not been tested in detail by the remote sensing community relative to more conventional pattern recognition techniques such as maximum likelihood classification. In this paper, we present several types of decision tree classification algorithms arid evaluate them on three different remote sensing data sets. The decision tree classification algorithms tested include an univariate decision tree, a multivariate decision tree, and a hybrid decision tree capable of including several different types of classification algorithms within a single decision tree structure. Classification accuracies produced by each of these decision tree algorithms are compared with both maximum likelihood and linear discriminant function classifiers. Results from this analysis show that the decision tree algorithms consistently outperform the maximum likelihood and linear discriminant function classifiers in regard to classf — cation accuracy. In particular, the hybrid tree consistently produced the highest classification accuracies for the data sets tested. More generally, the results from this work show that decision trees have several advantages for remote sensing applications by virtue of their relatively simple, explicit, and intuitive classification structure. Further, decision tree algorithms are strictly nonparametric and, therefore, make no assumptions regarding the distribution of input data, and are flexible and robust with respect to nonlinear and noisy relations among input features and class labels.

A Simple, Universal Colorimetric Assay for Endonuclease/Methyltransferase Activity and Inhibition Based on an Enzyme-Responsive Nanoparticle System

An enzyme responsive nanoparticle system that uses a DNA-gold nanoparticle (AuNP) assembly as the substrate has been developed for the simple, sensitive, and universal monitoring of restriction endonucleases in real time. This new assay takes advantage of the palindromic recognition sequence of the restriction nucleases and the unique optical properties of AuNPs and is simpler than the procedure previously described by by Xu et al. (Angew. Chem. Int. Ed. Engl. 2007, 46, 3468-3470). Because it involves only one type of ssDNA modified AuNPs, this assay can be directed toward most of the endonucleases by simply changing the recognition sequence found within the linker DNA. In addition, the endonuclease activity could be quantitatively analyzed by the value of the reciprocal of hydrolysis half time (t(1/2)(-1). Furthermore, our new design could also be applied to the assay of methyltransferase activity since the methylation of DNA inhibits its cleavage by the corresponding restriction endonuclease, and thus, this new methodology can be easily adapted to high-throughput screening of methyltransferase inhibitors.