This research explores the automated classification of monolayer and few-layer MoS2 and WS2 nanostructures using texture analysis (TA) and neural networks. Three TA methods—grey level histogram (GLH), grey levels co-occurrence matrix (GLCOM), and run-length matrix (RLM)—were employed. Feature selection using the Fisher coefficient and classification using artificial neural networks (ANN) and linear discriminant analysis (LDA) were performed. RLM with ANN achieved the highest accuracy (89% for MoS2 and 95% for WS2), suggesting higher-order TA methods are superior for characterizing nanolayer thickness.
Publisher
Scientific Reports
Published On
Nov 26, 2020
Authors
Shrouq H. Aleithan, Doaa Mahmoud-Ghoneim
Tags
nanostructures
texture analysis
neural networks
MoS2
WS2
classification
feature selection
Related Publications
Explore these studies to deepen your understanding of the subject.
