The Geodesic K-Means Algorithm for Graph-Based Data Clustering

• Grant number: 23/12954-0
• Support Opportunities: Scholarships in Brazil - Scientific Initiation
• Start date: December 01, 2023
• End date: November 30, 2024
• Field of knowledge: Physical Sciences and Mathematics - Computer Science - Computing Methodologies and Techniques
• Principal Investigator: Alexandre Luís Magalhães Levada
• Grantee: Antonio Cicero Amorim de Azevedo
• Host Institution: Centro de Ciências Exatas e de Tecnologia (CCET). Universidade Federal de São Carlos (UFSCAR). São Carlos , SP, Brazil

Abstract

Data clustering is a fundamental technique in the field of machine learning and data analysis. Its importance lies in the fact that it is an unsupervised approach that allows identifying patterns and hidden structures in data, without the need for labels or prior information about the classes. One of the best-known algorithms for this purpose is K-means. Despite being widely used, it has limitations, for example, being able to detect only circular clusters. In this research project, we propose the development of a geodesic K-means algorithm, which replaces Euclidean distances with geodesic distances in graphs. With this, it is expected to achieve better results in data clustering compared to the standard K-means algorithm, which can be considered a scientific and technological advance in various machine learning and pattern recognition applications.