“…Partitioning clustering can be interpreted by the centroidal Voronoi tessellation method in mathematics ( Du and Wong, 2002 ). It can be further specified to -means ( Forgy, 1965 , Hartigan and Wong, 1979 , Lloyd, 1982 , MacQueen, 1967 ), -medians ( Charikar and Guha, 2002 ), and -modes ( Goyal and Aggarwal, 2017 ), where -means is the most popular. To implement those, one needs to express observations of the data in a metric space, such that a distance measure can be defined.…”