Real data

These datasets, originally compiled as a standard benchmark set in the work of Arbelaitz et al. (2013), span a diverse range of domains, sizes, feature dimensionalities, and class distributions. This diversity ensures a comprehensive evaluation of clustering algorithms under realistic conditions, including varying levels of noise, nonlinearity, and class imbalance. They encompass application areas such as biology, medicine, chemistry, speech recognition, and image analysis. Each dataset is fully labeled, enabling the computation of external clustering validity indices by providing the ground-truth class memberships for all observations.