Dynamic Oscillating Search Algorithm for Feature Selection

We introduce a new feature selection method suitable for non-monotonic criteria, i.e., for wrapper-based feature selection. Inspired by oscillating search, the dynamic oscillating search: (i) is deterministic, (ii) optimizes subset size, (iii) has built-in preference of smaller subsets, (iv) has hig...

Full description

Saved in:
Bibliographic Details
Main Authors: Somol, P., Novovicova, J., Grim, J., Pudil, P.
Format: Conference Proceeding
Language:English
Subjects:
Automation
Heuristic algorithms
Information theory
Optimization methods
Pattern recognition
Search methods
Search problems
Time measurement
Usability
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:We introduce a new feature selection method suitable for non-monotonic criteria, i.e., for wrapper-based feature selection. Inspired by oscillating search, the dynamic oscillating search: (i) is deterministic, (ii) optimizes subset size, (iii) has built-in preference of smaller subsets, (iv) has higher optimization performance than other sequential methods. We show that the new algorithm is capable of over-performing older methods not only in criterion maximization ability but in some cases also in obtaining subsets that generalize better.
ISSN:1051-4651
2831-7475
DOI:10.1109/ICPR.2008.4761773