Work

A Comparative Study of Feature Selection Methods for Stress Hotspot Classification in Materials

Year: 2018

Type: article

Abstract: The first step in constructing a machine learning model is defining the features of the dataset that can be used for optimal learning. In this work, we discuss feature selection methods, which can be used to build better models, as well as achieve model interpretability. We applied these methods in the context of stress hotspot classification problem, to determine what microstructural characteristics can cause stress to build up in certain grains during uniaxial tensile deformation. The results show how some feature selection techniques are biased and demonstrate a preferred technique to get feature rankings for physical interpretations.

Source: Integrating materials and manufacturing innovation

DOI: 10.1007/s40192-018-0109-8

Authors: Ankita Mangal, Elizabeth A. Holm

Institution: Carnegie Mellon University

Language: English

Topic: Machine Learning in Materials Science

Subfield: Materials Chemistry

Field: Materials Science

Domain: Physical Sciences

Open Access status: hybrid

Estimated APC paid: $3,790

Funder: National Science Foundation