Browse our site
About
People
Research Areas
Projects
Publications
Books
Book chapters
Journal articles
In proceedings
M. Sc. Dissertations
Ph. D. Dissertations
Technical reports
Seminars
News
You are here:
Home
Publications
View
Publication details
Go back
Publication details
Main information
Title:
Laplacian Normalization for Deriving Thematic Fuzzy Clusters with an Additive Spectral Approach
Publication date:
May 2013
Citation:
NaFeMi13
Abstract:
This paper presents a further investigation into computational properties of a novel fuzzy additive spectral clustering method, FADDIS, recently introduced by authors (Mirkin and Nascimento 2012). Specifically, we extend our analysis to "difficult" data structures from the recent literature and develop two synthetic data generators simulating affinity data of Gaussian clusters and genuine additive similarity data, with a controlled level of noise. The FADDIS is experimentally verified on these data in comparison with two state-of-the art fuzzy clustering methods. The claimed ability of FADDIS to help in determining the right number of clusters is experimentally tested and the role of the pseudo-inverse Laplacian data transformation in this is highlighted. A potentially useful extension of the method to biclustering is introduced.
Journal
Authors:
Susana Nascimento
, Rui Felizardo, Boris Mirkin
Journal:
Expert Systems
Publisher:
Wiley
Address:
-
Volume:
30
Number:
4
Pages:
294-305
ISBN:
-
ISSN:
-
Note:
doi: 10.1111/exsy.12027
Url address:
http://onlinelibrary.wiley.com/doi/10.1111/exsy.12027/abstract
Export formats
Plain text:
Susana Nascimento and Rui Felizardo and Boris Mirkin, Laplacian Normalization for Deriving Thematic Fuzzy Clusters with an Additive Spectral Approach, Expert Systems, Vol. 30, No. 4, Pag. 294-305, Wiley, <i>doi: 10.1111/exsy.12027</i>, (http://onlinelibrary.wiley.com/doi/10.1111/exsy.12027/abstract), May 2013.
HTML:
<b><a href="/people/members/view.php?code=4d69262d034cb8174d039bea8d970836" class="author">Susana Nascimento</a>, Rui Felizardo and Boris Mirkin</b>, <u>Laplacian Normalization for Deriving Thematic Fuzzy Clusters with an Additive Spectral Approach</u>, Expert Systems, Vol. 30, No. 4, Pag. 294-305, <a href="http://www.wiley.com" title="Link to external entity..." target="_blank" class="publisher">Wiley</a>, <i>doi: 10.1111/exsy.12027</i>, (<a href="http://onlinelibrary.wiley.com/doi/10.1111/exsy.12027/abstract" target="_blank">url</a>), May 2013.
BibTeX:
@article {NaFeMi13, author = {Susana Nascimento and Rui Felizardo and Boris Mirkin}, title = {Laplacian Normalization for Deriving Thematic Fuzzy Clusters with an Additive Spectral Approach}, journal = {Expert Systems}, publisher = {Wiley}, volume = {30}, number = {4}, pages = {294-305}, note = {doi: 10.1111/exsy.12027}, url = {http://onlinelibrary.wiley.com/doi/10.1111/exsy.12027/abstract}, abstract = {This paper presents a further investigation into computational properties of a novel fuzzy additive spectral clustering method, FADDIS, recently introduced by authors (Mirkin and Nascimento 2012). Specifically, we extend our analysis to "difficult" data structures from the recent literature and develop two synthetic data generators simulating affinity data of Gaussian clusters and genuine additive similarity data, with a controlled level of noise. The FADDIS is experimentally verified on these data in comparison with two state-of-the art fuzzy clustering methods. The claimed ability of FADDIS to help in determining the right number of clusters is experimentally tested and the role of the pseudo-inverse Laplacian data transformation in this is highlighted. A potentially useful extension of the method to biclustering is introduced.}, keywords = {Relational fuzzy clustering; spectral fuzzy clustering; Laplacian normalization; number of clusters}, month = {May}, year = {2013}, }
Publication's urls
Full url:
/publications/view.php?code=d54129d7f318976e15e0370837cf7690
Friendly url:
/publications/view.php?code=NaFeMi13
Go back
Departamento de Informática, FCT/UNL
Quinta da Torre 2829-516 CAPARICA - Portugal
Tel. (+351) 21 294 8536 FAX (+351) 21 294 8541