Integrating Clustering and Classification for Estimating Process Variables in Materials Science.
Aparna S. Varde, Elke Angelika Rundensteiner, Carolina Ruiz, David C. Brown, Mohammed Maniruzzaman, Richard D. Sisson · National Conference on Artificial Intelligence · 2006
The results of experiments in scientific domains such as Materials Science are often depicted as graphs. The graphs we refer to plot a dependent versus an independent variable showing the behavior of the experimental processes [5, 11]. They serve as good visual tools for analysis and comparison of the corresponding processes. Performing an experiment in a laboratory and plotting such graphs consumes significant time and resources motivating the need for computational estimation. This is precisely the aim of this research. More specifically, the research goals are as follows: • Given the input conditions of an experimental process, estimate the resulting graph. • Given the desired graph in an experimental process, estimate the input conditions to obtain it.