U-Control Chart Based Differential Evolution Clustering for Determining the Number of Cluster in k-Means

The automatic clustering differential evolution (ACDE) is one of the clustering methods that are able to determine the cluster number automatically. However, ACDE still makes use of the manual strategy to determine k activation threshold thereby affecting its performance. In this study, the ACDE problem will be ameliorated using the u-control chart (UCC) then the cluster number generated from ACDE will be fed to k-means. The performance of the proposed method was tested using six public datasets from the UCI repository about academic efficiency (AE) and evaluated with Davies Bouldin Index (DBI) and Cosine Similarity (CS) measure. The results show that the proposed method yields excellent performance compared to prior researches.

• Autores: Silva, Jesús; Pineda Lezama, Omar Bonerge; Varela, Noel; García Guiliany, Jesús; Steffens Sanabria, Ernesto; Sánchez Otero, Madelin; Álvarez Rojas, Vladimir
• Tipo de recurso: http://purl.org/coar/resource_type/c_816b
• Fecha de publicación: 2019
• Institución: Corporación Universidad de la Costa
• Repositorio: REDICUC - Repositorio CUC
• Idioma: eng
• OAI Identifier: oai:repositorio.cuc.edu.co:11323/5136
• Acceso en línea: https://hdl.handle.net/11323/5136; https://repositorio.cuc.edu.co/
• Palabra clave: K-means; Automatic clustering; Differential evolution; K activation threshold; U control chart; Academic efficiency (AE)
• Rights: openAccess
• License: CC0 1.0 Universal