Search

As interdisciplinary science is flourishing because of materials informatics and additional factors; a systematic way is required for expressing knowledge and facilitating communication between scientists in various fields. A function decomposition tree is such a representation, but domain scientists face difficulty in constructing it. Thus, this study cites the general problems encountered by beginners in generating function decomposition trees and proposes a new function decomposition representation method based on a causality-first perspective for resolution of these problems. The causality-first decomposition tree was obtained from a workflow expressed according to the processing sequence. Moreover, we developed a program that performed automatic conversion using the features of the causality-first decomposition trees. The proposed method was applied to materials informatics to demonstrate the systematic representation of expert knowledge and its usefullness., Comment: 41 page, 13 figures

We propose a framework called HyperVAE for encoding distributions of distributions. When a target distribution is modeled by a VAE, its neural network parameters \theta is drawn from a distribution p(\theta) which is modeled by a hyper-level VAE. We propose a variational inference using Gaussian mixture models to implicitly encode the parameters \theta into a low dimensional Gaussian distribution. Given a target distribution, we predict the posterior distribution of the latent code, then use a matrix-network decoder to generate a posterior distribution q(\theta). HyperVAE can encode the parameters \theta in full in contrast to common hyper-networks practices, which generate only the scale and bias vectors as target-network parameters. Thus HyperVAE preserves much more information about the model for each task in the latent space. We discuss HyperVAE using the minimum description length (MDL) principle and show that it helps HyperVAE to generalize. We evaluate HyperVAE in density estimation tasks, outlier detection and discovery of novel design classes, demonstrating its efficacy., Comment: Accepted ECML-2021

We propose a data-driven method to extract dissimilarity between materials, with respect to a given target physical property. The technique is based on an ensemble method with Kernel ridge regression as the predicting model; multiple random subset sampling of the materials is done to generate prediction models and the corresponding contributions of the reference training materials in detail. The distribution of the predicted values for each material can be approximated by a Gaussian mixture model. The reference training materials contributed to the prediction model that accurately predicts the physical property value of a specific material, are considered to be similar to that material, or vice versa. Evaluations using synthesized data demonstrate that the proposed method can effectively measure the dissimilarity between data instances. An application of the analysis method on the data of Curie temperature (TC) of binary 3d transition metal 4f rare earth binary alloys also reveals meaningful results on the relations between the materials. The proposed method can be considered as a potential tool for obtaining a deeper understanding of the structure of data, with respect to a target property, in particular., Comment: 10 pages, 3 figures

In this study, we establish a basis for selecting similarity measures when applying machine learning techniques to solve materials science problems. This selection is considered with an emphasis on the distinctiveness between materials that reflect their nature well. We perform a case study with a dataset of rare-earth transition metal crystalline compounds represented using the Orbital Field Matrix descriptor and the Coulomb Matrix descriptor. We perform predictions of the formation energies using k-nearest neighbors regression, ridge regression, and kernel ridge regression. Through detailed analyses of the yield prediction accuracy, we examine the relationship between the characteristics of the material representation and similarity measures, and the complexity of the energy function they can capture. Empirical experiments and theoretical analysis reveal that similarity measures and kernels that minimize the loss of materials distinctiveness improve the prediction performance.

A method has been developed to measure the similarity between materials, focusing on specific physical properties. The information obtained can be utilized to understand the underlying mechanisms and support the prediction of the physical properties of materials. The method consists of three steps: variable evaluation based on nonlinear regression, regression-based clustering, and similarity measurement with a committee machine constructed from the clustering results. Three data sets of well characterized crystalline materials represented by critical atomic predicting variables are used as test beds. Herein, the focus is on the formation energy, lattice parameter and Curie temperature of the examined materials. Based on the information obtained on the similarities between the materials, a hierarchical clustering technique is applied to learn the cluster structures of the materials that facilitate interpretation of the mechanism, and an improvement in the regression models is introduced to predict the physical properties of the materials. The experiments show that rational and meaningful group structures can be obtained and that the prediction accuracy of the materials' physical properties can be significantly increased, confirming the rationality of the proposed similarity measure., identifier:https://dspace.jaist.ac.jp/dspace/handle/10119/16010

A method has been developed to measure the similarity between materials, focusing on specific physical properties. The information obtained can be utilized to understand the underlying mechanisms and support the prediction of the physical properties of materials. The method consists of three steps: variable evaluation based on nonlinear regression, regression-based clustering, and similarity measurement with a committee machine constructed from the clustering results. Three data sets of well characterized crystalline materials represented by critical atomic predicting variables are used as test beds. Herein, the focus is on the formation energy, lattice parameter and Curie temperature of the examined materials. Based on the information obtained on the similarities between the materials, a hierarchical clustering technique is applied to learn the cluster structures of the materials that facilitate interpretation of the mechanism, and an improvement in the regression models is introduced to predict the physical properties of the materials. The experiments show that rational and meaningful group structures can be obtained and that the prediction accuracy of the materials' physical properties can be significantly increased, confirming the rationality of the proposed similarity measure.

We propose a novel representation of materials named an ‘orbital-field matrix (OFM)’, which is based on the distribution of valence shell electrons. We demonstrate that this new representationcan be highly useful in mining material data. Experimental investigation shows that the formationenergies of crystalline materials, atomization energies of molecular materials, and local magneticmoments of the constituent atoms in bimetal alloys of a lanthanide metal and transition-metal can be predicted with high accuracy using the OFM. Knowledge regarding the role of the coordinationnumbers of the transition-metal and lanthanide elements in determining the local magnetic moments of the transition-metal sites can be acquired directly from decision tree regressionanalyses using the OFM., identifier:https://dspace.jaist.ac.jp/dspace/handle/10119/16009

We propose a novel representation of materials named an ‘orbital-field matrix (OFM)’, which is based on the distribution of valence shell electrons. We demonstrate that this new representationcan be highly useful in mining material data. Experimental investigation shows that the formationenergies of crystalline materials, atomization energies of molecular materials, and local magneticmoments of the constituent atoms in bimetal alloys of a lanthanide metal and transition-metal can be predicted with high accuracy using the OFM. Knowledge regarding the role of the coordinationnumbers of the transition-metal and lanthanide elements in determining the local magnetic moments of the transition-metal sites can be acquired directly from decision tree regressionanalyses using the OFM.

We demonstrate that knowledge of chemical physics on a materials system can be automatically extracted from first-principles calculations using a data mining technique; this information can then be utilized to construct a simple empirical atomic potential model. By using unsupervised learning of the generative Gaussian mixture model, physically meaningful patterns of atomic local chemical environments can be detected automatically. Based on the obtained information regarding these atomic patterns, we propose a chemical-structure-dependent linear mixture model for estimating the atomic potential energy. Our experiments show that the proposed mixture model significantly improves the accuracy of the prediction of the potential energy surface for complex systems that possess a large diversity in their local structures., identifier:https://dspace.jaist.ac.jp/dspace/handle/10119/14785

The role of coordinators in highly knowledge-intensive international business has been increasingly portrayed as filling the communication, cross-cultural, social gaps; or facilitators of knowledge sharing and knowledge transfer. However, they do not mention the process coordinators cooperate with partners to create new knowledge; whereas a critical issue is to facilitate the collaboration among partners in international and cross-cultural context. Our study bridges this gap by studying the knowledge-bridging process of bridge System Engineers (bridge SEs) in software offshore development context. Our analysis pointed out that beside required knowledge, bridge SEs utilized background of long term residence or study abroad; and “bridging-knowledge” to adjust communication contents before information is sent from one side to another. Based on the theoretical work of Nonaka and Takeuchi (1995) and empirical evidence of bridge SEs in Software Offshoring from Japan to Vietnam; we further develop the model of Knowledge-bridging process to show how the bridge SEs, the vendor and the client interact to create technological, business, bridging knowledge and decrease the cultural gaps., identifier:https://dspace.jaist.ac.jp/dspace/handle/10119/12354

The role of coordinators in highly knowledge-intensive international business has been increasingly portrayed as filling the communication, cross-cultural, social gaps; or facilitators of knowledge sharing and knowledge transfer. However, they do not mention the process coordinators cooperate with partners to create new knowledge; whereas a critical issue is to facilitate the collaboration among partners in international and cross-cultural context. Our study bridges this gap by studying the knowledge-bridging process of bridge System Engineers (bridge SEs) in software offshore development context. Our analysis pointed out that beside required knowledge, bridge SEs utilized background of long term residence or study abroad; and “bridging-knowledge” to adjust communication contents before information is sent from one side to another. Based on the theoretical work of Nonaka and Takeuchi (1995) and empirical evidence of bridge SEs in Software Offshoring from Japan to Vietnam; we further develop the model of Knowledge-bridging process to show how the bridge SEs, the vendor and the client interact to create technological, business, bridging knowledge and decrease the cultural gaps.

We develop a method that combines data mining and first principles calculation to guide the designing of distorted cubane Mn^<4+>Mn^<3+>_3 single molecule magnets. The essential idea of the method is a process consisting of sparse regressions and cross-validation for analyzing calculated data of the materials. The method allows us to demonstrate that the exchange coupling between Mn^<4+> and Mn^<3+> ions can be predicted from the electronegativities of constituent ligands and the structural features of the molecule by a linear regression model with high accuracy. The relations between the structural features and magnetic properties of the materials are quantitatively and consistently evaluated and presented by a graph. We also discuss the properties of the materials and guide the material design basing on the obtained resutls.

What is structure of water surrounding proteins remains as one of fundamental unsolved problems of science. Methods in biophysics only provide qualitative description of the structure and thus clarifying the collective phenomena of a huge number of water molecules is still beyond intuition in biophysics. We introduce a simulation-based data mining approach that quantitatively model the structure of water surrounding a protein as clusters of water molecules having similar moving behavior. The paper presents and explains how the advances of AI technique can potentially solve this challenging data-intensive problem., identifier:https://dspace.jaist.ac.jp/dspace/handle/10119/10332

Small clusters on substrates usually exhibit large numbers of configurations separated by relatively small barriers and easily interconvert between such configurations, known as structural fluxionality. We investigate here this property in hybrid catalytic structure: small Pt clusters adsorbed on single-wall carbon nanotube (SWNT) support using density functional calculations. We find that the Pt_4 clusters adsorbed on SWNT support exhibit several energetically accessible structural isomers with rather low-energy barriers, resulting in the high degree of structural fluxionality. We find that curvature of SWNT and charge redistribution play important roles in the variation in structure of Pt_4 cluster on SWNT. The high degree of structural fluxionality allows the Pt_4 clusters on SWNT to interact easily with environmental gas molecules such as CO by adapting their structures. The change in electronic structure via molecular adsorption due to the structural fluxionality and the variation in structure caused by changes in electronic structure are strongly interrelated resulting in the wide variety of dynamic reactions of CO molecules with Pt_4 clusters., identifier:https://dspace.jaist.ac.jp/dspace/handle/10119/10311

Small clusters on substrates usually exhibit large numbers of configurations separated by relatively small barriers and easily interconvert between such configurations, known as structural fluxionality. We investigate here this property in hybrid catalytic structure: small Pt clusters adsorbed on single-wall carbon nanotube (SWNT) support using density functional calculations. We find that the Pt_4 clusters adsorbed on SWNT support exhibit several energetically accessible structural isomers with rather low-energy barriers, resulting in the high degree of structural fluxionality. We find that curvature of SWNT and charge redistribution play important roles in the variation in structure of Pt_4 cluster on SWNT. The high degree of structural fluxionality allows the Pt_4 clusters on SWNT to interact easily with environmental gas molecules such as CO by adapting their structures. The change in electronic structure via molecular adsorption due to the structural fluxionality and the variation in structure caused by changes in electronic structure are strongly interrelated resulting in the wide variety of dynamic reactions of CO molecules with Pt_4 clusters.