Tokyo University of Science

About: Tokyo University of Science is a education organization based out in Tokyo, Japan. It is known for research contribution in the topics: Thin film & Enantioselective synthesis. The organization has 15800 authors who have published 24147 publications receiving 438081 citations. The organization is also known as: Tōkyō Rika Daigaku & Science University of Tokyo.

Bankruptcy prediction using imaged financial ratios and convolutional neural networks

Abstract: Convolutional neural networks are being applied to identification problems in a variety of fields, and in some areas are showing higher discrimination accuracies than conventional methods However, applications of convolutional neural networks to financial analyses have only been reported in a small number of studies on the prediction of stock price movements The reason for this seems to be that convolutional neural networks are more suitable for application to images and less suitable for general numerical data including financial statements Hence, in this research, an attempt is made to apply a convolutional neural network to the prediction of corporate bankruptcy, which in most cases is treated as a two-class classification problem We use the financial statements (balance sheets and profit-and-loss statements) of 102 companies that have been delisted from the Japanese stock market due to de facto bankruptcy as well as the financial statements of 2062 currently listed companies over four financial periods In our proposed method, a set of financial ratios are derived from the financial statements and represented as a grayscale image The image generated by this process is utilized for training and testing a convolutional neural network Moreover, the size of the dataset is increased using the weighted averages to create synthetic data points A total of 7520 images for the bankrupt and continuing enterprises classes are used for training the convolutional neural network based on GoogLeNet Bankruptcy predictions through the trained network are shown to have a higher performance compared to methods using decision trees, linear discriminant analysis, support vector machines, multi-layer perceptron, AdaBoost, or Altman’s Z′′-score

Structures of the reactive intermediates in organocatalysis with diarylprolinol ethers

Abstract: Structures of the reactive intermediates (enamines and iminium ions) of organocatalysis with diarylprolinol derivatives have been determined. To this end, diarylprolinol methyl and silyl ethers, 1, and aldehydes, PhCH2CHO, tBuCH2CHO, PhCH=CHCHO, are condensed to the corresponding enamines, A and 3 (Scheme 2), and cinnamoylidene iminium salts, B and 4 (Scheme 3). These are isolated and fully characterized by melting/decomposition points, [α]D, elemental analysis, IR and NMR spectroscopy, and high-resolution mass spectrometry (HR-MS). Salts with BF4, PF6, SbF6, and the weakly coordinating Al[OC(CF3)3]4 anion were prepared. X-Ray crystal structures of an enamine and of six iminium salts have been obtained and are described herein (Figs. 2 and 4–8, and Tables 2 and 7) and in a previous preliminary communication (Helv. Chim. Acta2008, 91, 1999). According to the NMR spectra (in CDCl3, (D6)DMSO, (D6)acetone, or CD3OD; Table 1), the major isomers 4 of the iminium salts have (E)-configuration of the exocyclic NC(1′) bond, but there are up to 11% of the (Z)-isomer present in these solutions (Fig. 1). In all crystal structures, the iminium ions have (E)-configuration, and the conformation around the exocyclic N-CC-O bond is synclinal-exo (cf.C and L), with one of the phenyl groups over the pyrrolidine ring, and the RO group over the π-system. One of the meta-substituents (Me in 4b, CF3 in 4c and 4e) on a 3,5-disubstituted phenyl group is also located in the space above the π-system. DFT Calculations at various levels of theory (Tables 3–6) confirm that the experimentally determined structures (cf. Fig. 10) are by far (up to 8.3 kcal/mol) the most stable ones. Implications of the results with respect to the mechanism of organocatalysis by diarylprolinol derivatives are discussed.

Photocatalysis and solar hydrogen production

Abstract: Photocatalytic water splitting is a challenging reaction because it is an ultimate so- lution to energy and environmental issues. Recently, many new powdered photocatalysts for water splitting have been developed. For example, a NiO (0.2 wt %)/NaTaO 3 :La (2 %) photo- catalyst with a 4.1-eV band gap showed high activity for water splitting into H 2 and O 2 with an apparent quantum yield of 56 % at 270 nm. Overall water splitting under visible light ir- radiation has been achieved by construction of a Z-scheme photocatalysis system employing visible-light-driven photocatalysts, Ru/SrTiO 3 :Rh and BiVO 4 for H 2 and O 2 evolution, and an Fe 3+ /Fe 2+ redox couple as an electron relay. Moreover, highly efficient sulfide photocat- alysts for solar hydrogen production in the presence of electron donors were developed by making solid solutions of ZnS with AgInS 2 and CuInS 2 of narrow band gap semiconductors. Thus, the database of powdered photocatalysts for water splitting has become plentiful.