The choice of a dissimilarity measure between curves is a key point for clustering functional data. In this paper we propose to obtain the granulometric distribution functions of the original curves and then calculate the dissimilarities between the new functional data. Good results have been obtained with two real examples.
机构:
Univ Fed Rio de Janeiro, Ctr Tecnol, Sch Chem, Dept Chem Engn, Av Athos da Silveira Ramos 149,Bloco E, BR-21941909 Rio De Janeiro, RJ, BrazilUniv Fed Rio de Janeiro, Ctr Tecnol, Sch Chem, Dept Chem Engn, Av Athos da Silveira Ramos 149,Bloco E, BR-21941909 Rio De Janeiro, RJ, Brazil
Guimaraes, Andressa Azevedo
Klein, Tania Suaiden
论文数: 0引用数: 0
h-index: 0
机构:
Univ Fed Rio de Janeiro, Ctr Tecnol, Sch Chem, Dept Chem Engn, Av Athos da Silveira Ramos 149,Bloco E, BR-21941909 Rio De Janeiro, RJ, BrazilUniv Fed Rio de Janeiro, Ctr Tecnol, Sch Chem, Dept Chem Engn, Av Athos da Silveira Ramos 149,Bloco E, BR-21941909 Rio De Janeiro, RJ, Brazil
Klein, Tania Suaiden
Medronho, Ricardo de Andrade
论文数: 0引用数: 0
h-index: 0
机构:
Univ Fed Rio de Janeiro, Ctr Tecnol, Sch Chem, Dept Chem Engn, Av Athos da Silveira Ramos 149,Bloco E, BR-21941909 Rio De Janeiro, RJ, BrazilUniv Fed Rio de Janeiro, Ctr Tecnol, Sch Chem, Dept Chem Engn, Av Athos da Silveira Ramos 149,Bloco E, BR-21941909 Rio De Janeiro, RJ, Brazil