Comparing transfer learning to feature optimization in microstructure classification

Debanshu Banerjee; Taylor D Sparks

doi:10.1016/j.isci.2022.103774

Comparing transfer learning to feature optimization in microstructure classification

iScience. 2022 Jan 15;25(2):103774. doi: 10.1016/j.isci.2022.103774. eCollection 2022 Feb 18.

Authors

Debanshu Banerjee¹, Taylor D Sparks²

Affiliations

¹ Metallurgical and Material Engineering Department, Jadavpur University, Kolkata, West Bengal 700032, India.
² Department of Materials Science and Engineering, The University of Utah, Salt Lake City, UT 84112, USA.

Abstract

Human analysis of research data is slow and inefficient. In recent years, machine learning tools have advanced our capability to perform tasks normally carried out by humans, such as image segmentation and classification. In this work, we seek to further improve binary classification models for high-throughput identification of different microstructural morphologies. We utilize a dataset with limited observations (133 dendritic structures, 444 non-dendritic) and employ data augmentation via rotation and translation to enhance the dataset six-fold. Then, transfer learning is carried out using pre-trained networks VGG16, InceptionV3, and Xception achieving only moderate F1 scores (0.801-0.822). We hypothesize that feature engineering could yield better results than transfer learning alone. To test this, we employ a new nature-inspired feature optimization algorithm, the Binary Red Deer Algorithm (BRDA), to carry out binary classification and observe F1 scores in the range of 0.96.

Keywords: Computational materials science; Computer modeling; Materials science.