Publication

Abstract :

This chapter offers a novel method for using graph theory and machine learning (ML) to analyze monomer structures. We selected 40 monomer structures from two different polymer classes namely aromatic and aliphatic polymers and converted them into molecular graphs, and evaluated 10 topological indices based on distance measures. Our primary objective was to classify these monomers into aliphatic and aromatic polymers using ML models. We generated input data for the ML classification task by converting the molecular graphs into vector representa tions. Additionally, we discuss the broader relevance of graph theory, including its application in ECG data classification using visibility graphs. This chapter highlights the possibility of using ML approaches to graph theory for sophisticated chemical research and other scientific applications