The problem addressed in this paper concerns the multi-classifier generation by a Random Subspace method. In the random subspace method the classifiers are constructed in random subspaces of the data feature space. In this work we propose an evolved feature weighting approach: in each subspace the features are multiplied by a weight factor for minimizing the error rate in the training set. An efficient method based on Particle Swarm Optimization is here proposed for finding a set of weights for each feature in each subspace. The performance improvement with respect to the state-of-the-art approaches is validated through experiments with several benchmark datasets.
Evolved feature weighting for random subspace classifier / L. Nanni; A. Lumini. - In: IEEE TRANSACTIONS ON NEURAL NETWORKS. - ISSN 1045-9227. - STAMPA. - 19:(2008), pp. 363-366. [10.1109/TNN.2007.910737]
Evolved feature weighting for random subspace classifier
NANNI, LORIS;LUMINI, ALESSANDRA
2008
Abstract
The problem addressed in this paper concerns the multi-classifier generation by a Random Subspace method. In the random subspace method the classifiers are constructed in random subspaces of the data feature space. In this work we propose an evolved feature weighting approach: in each subspace the features are multiplied by a weight factor for minimizing the error rate in the training set. An efficient method based on Particle Swarm Optimization is here proposed for finding a set of weights for each feature in each subspace. The performance improvement with respect to the state-of-the-art approaches is validated through experiments with several benchmark datasets.I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.