Carregant...
Carregant...

Vés al contingut (premeu Retorn)

Unsupervised feature selection by means of external validity indices

Autor
Bejar, J.
Tipus d'activitat
Document cientificotècnic
Data
2013-02-12
Codi
LSI-13-3-R
Projecte finançador
SUstainable and PERsuasive Human Users moBility in future cities
Sistema inteligente IWALKER: rehabilitación colaborativa
Repositori
http://hdl.handle.net/2117/23413 Obrir en finestra nova
URL
http://www.lsi.upc.edu/~techreps/files/R13-3.zip Obrir en finestra nova
Resum
Feature selection for unsupervised data is a difficult task because a reference partition is not available to evaluate the relevance of the features. Recently, different proposals of methods for consensus clustering have used external validity indices to assess the agreement among partitions obtained by clustering algorithms with different parameter values. Theses indices are independent of the characteristics of the attributes describing the data, the way the partitions are represented or the s...
Citació
Bejar, J. "Unsupervised feature selection by means of external validity indices". 2013.
Paraules clau
Clustering, Data mining, Unsupervised feature selection, Validity indices
Grup de recerca
IDEAI-UPC Intelligent Data Science and Artificial Intelligence
KEMLG - Grup d´Enginyeria del Coneixement i Aprenentatge Automàtic

Participants

Arxius