Publication details

Improving Sequential Feature Selection Methods Performance by Means of Hybridization

Conference Paper (international conference)

Somol Petr, Novovičová Jana, Pudil Pavel


serial: Proc. 6th IASTED Int. Conf. on Advances in Computer Science and Engineering , Eds: Rafea 

action: Advances in Computer Science and Engineering, (Sharm El Sheikh, EG, 15.03.2010-17.03.2010)

research: CEZ:AV0Z10750506

project(s): 1M0572, GA MŠk, 2C06019, GA MŠk, GA102/08/0593, GA ČR, GA102/07/1594, GA ČR

keywords: Feature selection, sequential search, hybrid methods, classification performance, subset search, statistical pattern recognition

preview: Download

abstract (eng):

In this paper we propose the general scheme of defining hybrid feature selection algorithms based on standard sequential search with the aim to improve feature selection performance, especially on high-dimensional or large-sample data. We show experimentally that “hybridization” has not only the potential to dramatically reduce FS search time, but in some cases also to actually improve classifier generalization, i.e., its classification performance on previously unknown data.

RIV: BD