From endoscopic imaging and knowledge to semantic formal images
VIEW'06 Proceedings of the 1st first visual information expert conference on Pixelization paradigm
EVCLUS: evidential clustering of proximity data
IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics
Possibilistic pattern recognition in a digestive database for mining imperfect data
WSEAS TRANSACTIONS on SYSTEMS
Quality evaluation of defects with indefinite or unlimited borders
ICS'09 Proceedings of the 13th WSEAS international conference on Systems
Fusion of possibilistic sources of evidences for pattern recognition
Integrated Computer-Aided Engineering
Gastroenterology dataset clustering using possibilistic Kohonen maps
WSEAS Transactions on Information Science and Applications
Towards a possibilistic processing of missing values under complex conditions
WSEAS Transactions on Information Science and Applications
Towards a possibilistic classification of gastroenterology patterns in a complex environment
WSEAS TRANSACTIONS on SYSTEMS
Hi-index | 0.00 |
An approach for clustering objects containing imperfect and heterogeneously-assigned data is proposed. This approach depends mainly on possibility theory to estimate the similarity between objects, and on belief theory and multidimensional scaling methods to assign relevant classes to them. This unsupervised clustering method has been applied to a medical database and robust results have been obtained with the absence of any a priori medical knowledge, and without knowing the key attributes of the concerned pathologies.