Please use this identifier to cite or link to this item:
|Title:||A spatially-constrained normalized gamma process for data clustering||Authors:||Korkinof, Dimitrios
Chatzis, Sotirios P.
|Keywords:||Information systems;Artificial intelligence;Markov random fields||Category:||Mechanical Engineering||Field:||Engineering and Technology||Issue Date:||2012||Publisher:||Springer||Source:||Artificial intelligence applications and innovations: 8th IFIP WG 12.5 international conference, AIAI 2012, Halkidiki, Greece, September 27-30, 2012, Proceedings, Part I, Pages 337-346||Abstract:||In this work, we propose a novel nonparametric Bayesian method for clustering of data with spatial interdependencies. Specifically, we devise a novel normalized Gamma process, regulated by a simplified (pointwise) Markov random field (Gibbsian) distribution with a countably infinite number of states. As a result of its construction, the proposed model allows for introducing spatial dependencies in the clustering mechanics of the normalized Gamma process, thus yielding a novel nonparametric Bayesian method for spatial data clustering. We derive an efficient truncated variational Bayesian algorithm for model inference. We examine the efficacy of our approach by considering an image segmentation application using a real-world dataset. We show that our approach outperforms related methods from the field of Bayesian nonparametrics, including the infinite hidden Markov random field model, and the Dirichlet process prior||URI:||http://ktisis.cut.ac.cy/handle/10488/7205||ISBN:||978-3-642-33408-5 (print)
|DOI:||10.1007/978-3-642-33409-2_35||Rights:||© 2012 IFIP International Federation for Information Processing||Type:||Book Chapter|
|Appears in Collections:||Κεφάλαια βιβλίων/Book chapters|
Show full item record
checked on Nov 16, 2017
Page view(s) 5029
checked on Nov 20, 2017
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.