Τίτλος:
Detecting hyperplane clusters with adaptive possibilistic clustering
Γλώσσες Τεκμηρίου:
Αγγλικά
Περίληψη:
In this paper the problem of detecting clusters whose points are spread
along an (1 1)-dimensional hyperplane in an 1-dimensional space is
considered. More specifically, the recently proposed adaptive
possibilistic c-means algorithm is modified in order to cope with this
type of clusters. The main advantage of the proposed method is that it
does not require a priori knowledge of the exact number of clusters.
Instead, it begins with an overestimated number of them and
(potentially) ends up with the true number of them. Preliminary results
of the proposed algorithm on both synthetic and real data verify its
validity.
Συγγραφείς:
Koutroumbas, K. D.
Xenaki, S. D.
Rontogiannis, A. A.
Εκδότης:
ASSOCIATION FOR COMPUTING MACHINERY
Τίτλος συνεδρίου:
9TH HELLENIC CONFERENCE ON ARTIFICIAL INTELLIGENCE (SETN 2016)
Λέξεις-κλειδιά:
possibilistic clustering; adaptivity; hyperplane clusters
DOI:
10.1145/2903220.2903236
