Graph-based Clustering Index for Topology and Classification Analysis

Jose G. Fernandes; Frederico Coelho; Antonio P. Braga

doi:10.20906/SBAI-SBSE-2023/4035

Jose G. Fernandes Graduate Program in Electrical Engineering, Universidade Federal de Minas Gerais, Belo Horizonte, MG
Frederico Coelho Department of Eletronic and Engineering, Universidade Federal de Minas Gerais, Belo Horizonte, MG
Antonio P. Braga Department of Eletronic and Engineering, Universidade Federal de Minas Gerais, Belo Horizonte, MG

DOI: https://doi.org/10.20906/SBAI-SBSE-2023/4035

Keywords: Clustering Index, Supervised Learning, Gabriel Graph, Machine Learning, Local Clustering

Abstract

This work proposes a quality index based on a graph of distance relationships, the Gabriel Graph, to analyze the performance of classification models. The results have shown a consistent correlation between the quality index and the model’s predictions, both at an individual and global level. These findings emphasize the importance of considering the data space to explain and optimize the performance of classification models.