Adaptive branch and bound algorithm for selecting optimal features

doi:10.1016/j.patrec.2007.02.015

Adaptive branch and bound algorithm for selecting optimal features

2007-09-01

56

PRE

AI

S

Songyot Nakariyakul *

D

David Casasent

DOI：10.1016/j.patrec.2007.02.015

Original

Original request for help

Save

Abstract

En 中文

We propose a new adaptive branch and bound algorithm for selecting the optimal subset of features in pattern recognition applications. The algorithm improves the search speed by avoiding unnecessary criterion function calculations at nodes in the solution tree. Our algorithm includes the following new properties: (i) ordering the tree nodes by the significance of features during construction of the tree, Oil obtaining a large good initial bound by a floating search method, (iii) a new method to select an initial starting search level in the tree. and (iv) a new adaptive jump search strategy to select subsequent search levels to avoid redundant criterion function calculations. Our experimental results for four different databases demonstrate that our method is significantly faster than other versions of the branch and bound algorithm when the database has more than 30 features. (c) 2007 Elsevier B.V.. All rights reserved.

Keywords:

branch and bound algorithm

dimensionality reduction

feature selection

optimal subset search

Adaptive branch and bound algorithm for selecting optimal features

Abstract

Journal

Organization