Research Papers
The application of Principal Component Analysis to materials science data
Authors:
Changwon Suh,
Department of Materials Science and Engineering and Faculty of Information Technology
Rensselaer Polytechnic Institute, Troy NY 12180-3590 USA, US
Arun Rajagopalan,
Department of Materials Science and Engineering and Faculty of Information Technology
Rensselaer Polytechnic Institute, Troy NY 12180-3590 USA, US
Xiang Li,
Department of Materials Science and Engineering and Faculty of Information Technology
Rensselaer Polytechnic Institute, Troy NY 12180-3590 USA, US
Krishna Rajan
Department of Materials Science and Engineering and Faculty of Information Technology
Rensselaer Polytechnic Institute, Troy NY 12180-3590 USA, US
Abstract
The relationship between apparently disparate sets of data is a critical component of interpreting materials' behavior, especially in terms of assessing the impact of the microscopic characteristics of materials on their macroscopic or engineering behavior. In this paper we demonstrate the value of principal component analysis of property data associated with high temperature superconductivity to examine the statistical impact of the materials' intrinsic characteristics on high temperature superconducting behavior
How to Cite:
Suh, C., Rajagopalan, A., Li, X. and Rajan, K., 2006. The application of Principal Component Analysis to materials science data. Data Science Journal, 1(1), pp.19–26. DOI: http://doi.org/10.2481/dsj.1.19
Published on
05 Jan 2006.
Peer Reviewed
Downloads