A comparative study of feature selection methods for stress hotspot classification in materials
This work addresses stress hotspot classification in materials science, but it is incremental as it applies existing feature selection methods to a specific domain problem.
The study tackled the problem of identifying microstructural features that cause stress hotspots in materials under tensile deformation by comparing feature selection methods, finding that some techniques are biased and recommending a preferred one for interpretable rankings.
The first step in constructing a machine learning model is defining the features of the data set 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.