CIFASIS   20631
CENTRO INTERNACIONAL FRANCO ARGENTINO DE CIENCIAS DE LA INFORMACION Y DE SISTEMAS
Unidad Ejecutora - UE
artículos
Título:
Unsupervized Data-Driven Partitioning of Multiclass Problems
Autor/es:
HERNÁN C. AHUMADA; GUILLERMO L. GRINBLAT; PABLO M. GRANITTO
Revista:
LECTURE NOTES IN COMPUTER SCIENCE
Editorial:
Springer
Referencias:
Año: 2011 vol. 6791 p. 117 - 125
ISSN:
0302-9743
Resumen:
Many classification problems of high technological value are multiclass.
In the last years, several improved solutions based
on the combination of simple classifiers were introduced. An
interesting kind of methods creates a hierarchy of sub-problems
by clustering prototypes of each one of the classes, but the
solution produced by the clustering stage is heavily influenced
by the labels information. In this work we introduce a new
strategy to solve multiclass problems that makes more use of spatial
information than other methods. Based on our previous work
on imbalanced problems, we construct a hierarchy of subproblems,
but opposite to previous developments, based only on spatial
information and not using class labels at any time. We consider
different clustering methods (either agglomerative or
divisive) for this task. We use an SVM for each sub-problem (if needed,
because in several cases the clustering method directly
gives a subset with samples of a single class). Using publicly available
datasets we compare the new method with several previous
approaches, finding promising results.