Novelty detection with application to data streams

• Tipo: Artigo em Revista Científica Internacional
• Data: 2009

Autores

Eduardo Spinosa (Autor) Outra; João Gama (Autor) FEP; Andre Carvalho (Autor) Outra

Revista

Título: Intelligent Data Analysis

Vol. 13 Nº 1

Páginas: 405-422

ISSN: 1088-467X

Editora: IOS PRESS

Indexação

ISI Web of Knowledge - 42 Citações

ISI Web of Science

Scopus - 45 Citações

Classificação Científica

FOS: Ciências exactas e naturais > Ciências da computação e da informação

Outras Informações

ID Authenticus: P-003-QK0

DOI: 10.3233/ida-2009-0373

Abstract (EN): This paper presents and evaluates an approach to novelty detection that addresses it as the problem of identifying novel concepts in a continuous learning scenario, as an extension to a single-class classification problem. OLINDDA, an OnLIne Novelty and Drift Detection Algorithm that implements this approach, uses efficient standard clustering algorithms to continuously generate candidate clusters among examples that were not explained by the current known concepts. Clusters complying with a validation criterion that takes cohesiveness and representativeness into account are initially identified as concepts. By merging similar concepts, OLINDDA may enhance the representation of some concepts as it advances toward its final goal of describing novel emerging concepts in an unsupervised way. The proposed approach is experimentally evaluated by the use of several measures taken throughout the learning process. Results show that it is capable of identifying novel concepts that are pure and correspond to real classes, disregarding unrepresentative clusters and outliers.

Idioma: Inglês

Tipo (Avaliação Docente): Científica

Nº de páginas: 18