Analysis and visualization of category membership distribution in multivariate data

This paper reports on some advances in generic data processing procedures w ith focus on a specific materials discovery and design task. The task is to predict whether a new ternary materials system would be compound forming o r not, with the prediction to be based on knowledge of many other known exe mplars. The activities and results of three related efforts are described i n condensed form in this paper. In one effort, using a combination of clust ering and mapping procedures, an accuracy of more than 99% was attained in predicting the category status (compound forming or not) of new ternary sys tems. A second effort addressed the question of how to identify redundant o r superfluous features. A procedure for identifying the extent of functiona l dependency amongst features was developed. That procedure can be used to remove redundant features. A third effort addressed the question of how to obtain reduced dimension representations of multivariate data, albeit at th e cost of loss of some information. Visualizations of low-dimensional repre sentations can be helpful in building up holistic views of data space for u se in exploration and discovery of new materials. (C) 2000 Elsevier Science Ltd. All rights reserved.