Parameter tuning in the support vector machine and random forest and their performances in cross- and same-year crop classification using TerraSAR-X

This article describes the comparison of three different classification algorithms for mapping crops in Hokkaido, Japan, using TerraSAR-X data. In the study area, beans, beets, grasslands, maize, potatoes, and winter wheat were cultivated. Although classification maps are required for both management and estimation of agricultural disaster compensation, those techniques have yet to be established. Some supervised learning models may allow accurate classification. Therefore, comparisons among the classification and regression tree (CART), the support vector machine (SVM), and random forests (RF) were performed. SVM was the optimum algorithm in this study, achieving an overall accuracy of 89.1% for the same-year classification, which is the classification using the training data in 2009 to classify the test data in 2009, and 78.0% for the cross-year classification, which is the classification using the training data in 2009 to classify the data in 2012.     

Construction universality in purely asynchronous cellular automata

Universality in cellular automata (CAs), first studied by von Neumann, has attracted much research efforts over the years, especially for CA employing synchronous timing. This paper proposes a computation- and construction-universal CA with a von Neumann neighborhood that is updated in a purely asynchronous way, rather than by the conventional but less efficient way of simulating synchronous CAs on asynchronous CAs. The proposed asynchronous CA is capable of implementing self-reproducing machines. Our model employs strongly symmetric cells with 15 states.     

Characterization of a Maltogenic Amylase of Thermononospora viridis and Application in Branched Cyclodextrin Production

Some kinetic characteristics and actions on various cyclodextrins (CDs) of a maltogenic α-amylase of T. viridis (TVA) were examined to apply in the branched CD production. Michaelis constants (Km) for hydrolysis of α-, β- and γ-CDs by the enzyme were 6.5, 7.6 and 10.8 mM, and apparent molecular activities (k_θ) for these saccharides were 11.0, 67.2 and 432.8 s⁻¹, respectively. The (k_θ) values for various branched CDs were remarkably smaller than those for unbranched CDs. The TVA cleaved first the ring of maltosyl-β-CD, and the branched nonasaccharide formed was immediately degraded to give branched hexa- and penta-saccharides with simultaneous formation of smaller unbranched saccharides. As a minor action, the enzyme released a glucose molecule from the side chain of maltosyl-β-CD to give glucosyl-β-CD which was readily degraded to smaller saccarides. The enzyme had an ability to hydrolyze unbranched CDs preferentially in the presence of significant amounts of branched CDs. These characteristics of the enzyme are consistent with its potential industrial use in the branched CD production.     

Kinetic Characterization of Chimeric Cyclomaltodextrin Glucanotransferase from Genes of Two Alkalophilic Bacillus

The chimeric CGTase, which was constructed genetically with two β-CD forming type enzyme genes of different species of alkalophilic Bacillus, was characterized by comparing with the actions of parent enzymes. The final composition of CDs in the reaction digest from starch by the chimeric enzyme, especially in the yield of α-CD, was different from those by parent enzymes, and total yields of CDs by these enzymes were almost the same. The chimeric enzyme catalyzed the formation of β-CD as a major action from starch, the rapid synthesis of α-CD from other CDs and maltooligosaccharides and the slow degradation and interconversion of α-CD to others. From these results, the role of second and third segments in the enzyme molecules was discussed.     

Platinum on Carbon‐Catalyzed Precise Reduction Control of Trichloromethyl to Geminal‐Dichloromethyl Groups

Geminal‐dichloromethyl derivatives could be efficiently synthesized by the highly chemoselective platinum on carbon‐catalyzed mono‐dechlorination of trichloromethyl substrates in dimethylacetamide (DMA) as a specific solvent at 25 °C under a hydrogen atmosphere.