“…Partitional clustering methods, which divide the data according to natural classes present in it, have been used in a large variety of scientific disciplines and engineering applications, among them pattern recognition (Duda & Hart, 1973), learning theory (Moody & Darken, 1989), astrophysics (Dekel & West, 1985), medical imaging (Suzuki, Shibata, & Suto, 1995) and data processing (Phillips et al, 1995), machine translation of text (Cranias, Papageorgiou, & Piperdis, 1994), image compression (Karayiannis, 1994), satellite data analysis (Baraldi & Parmiggiani, 1995), automatic target recognition (Iokibe, 1994), and speech recognition (Kosaka & Sagayama, 1994) and analysis (Foote & Silverman, 1994).…”