For successful applications of machine learning in materials informatics, it is necessary to overcome the inaccuracy predictions ascribed insufficient amount data. In this study, we propose a transfer using crystal graph convolutional neural network (TL-CGCNN). Herein, TL-CGCNN pretrained with big data such as formation energies for structures, and then used predicting target properties relativ...

Abstract We present a method to structure liquid crystal network actuators based on selectively polymerizing the without any physical or hard masks in process compatible with microelectromechanical system (MEMS) technology. The standard glass-cell filling technique is used generate actuator films; subsequently, selected areas are exposed light and thus polymerized actuators. No further machinin...

calcium dichloride tetra urea was prepared by the reaction of calcium chloride with urea in aqueous solution. the crystals are monoclinic, a= 7.633, b= 12.45 1, c= 8.118 ?,? = 113.17, z = 4, space group p 2,/a. the crystal structure was determined by single crystal x-ray methods and refined to r= 0.041. the calcium atoms are coordinated to four oxygen atoms of urea and to two chloride ions. the...

This paper discusses the development of a system for the automated real-time measurement of crystal size distributions during crystallisation. An optimised selection of the Daubechies wavelet coefficients is used as input to a Multi–Layer Perceptron artificial neural network to characterise the crystal scale lengths. This technique gives significant advantages over the sampling-based measuremen...

20 IMR KINKEN Research Highlights 2009 Future Energy / Environmental Materials By systematic crystal structure refinements of characteristic superconductor, FeSe1-xTex (x= 0.5, 0.625, 0.75, 0.875) and FeSe by the powder neutron diffraction technique, we studied the relationship between crystal structre and superconductivity. In this work, we found the role of Fe-X network (X; calcogens, pnictog...