Improving a Genetic Clustering Approach with a CVI-Based Objective Function

• Caio Flexa UFPA
• Walisson Gomes UFPA
• Igor Moreira UFPA
• Reginaldo Santos UFPA
• Claudomiro Sales UFPA
• Moisés Silva UFPA

Resumo

Genetic-based clustering meta-heuristics are important bioinspired algorithms. One such technique, termed Genetic Algorithm for Decision Boundary Analysis (GADBA), was proposed to support Structural Health Monitoring (SHM) processes in bridges. GADBA is an unsupervised, non-parametric approach that groups data into natural clusters by means of a specialized objective function. Albeit it allows a competent identification of damage indicators of SHM-related data, it achieves lackluster results on more general clustering scenarios. This study improves the objective function of GADBA based on a Cluster Validity Index (CVI) named Mutual Equidistant-scattering Criterion (MEC) to expand its applicability to any real-world problem.

Palavras-chave: Genetic Algorithm, Automatic Clustering Algorithm, Decision Boundary Analysis, Mutual Equidistant-scattering Criterion