2009
DOI: 10.1016/j.ins.2009.07.002
|View full text |Cite
|
Sign up to set email alerts
|

Feature selection via Boolean independent component analysis

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1
1

Citation Types

0
6
0

Year Published

2011
2011
2014
2014

Publication Types

Select...
5
2
1

Relationship

1
7

Authors

Journals

citations
Cited by 12 publications
(6 citation statements)
references
References 68 publications
0
6
0
Order By: Relevance
“…In the last decade, metaheuristic methods such as tabu search [55,62], simulated annealing [10,33], genetic algorithms [17,42,47,54,57,61] have also been applied to solve the feature subset selection problem. In addition, there are feature selection methods based on rough set theory [4,7,19,58,63] and on Boolean independent component analysis [1].…”
Section: Overview Of Feature Selection Methodsmentioning
confidence: 99%
“…In the last decade, metaheuristic methods such as tabu search [55,62], simulated annealing [10,33], genetic algorithms [17,42,47,54,57,61] have also been applied to solve the feature subset selection problem. In addition, there are feature selection methods based on rough set theory [4,7,19,58,63] and on Boolean independent component analysis [1].…”
Section: Overview Of Feature Selection Methodsmentioning
confidence: 99%
“…The family is named BICA [16] and the algorithms for extracting these components are based on peculiar neural networks; Fig. 4.…”
Section: The Pram Architecturementioning
confidence: 99%
“…On the other hand, filter method uses some quality measure which is independent of the performance of the learning algorithm [8,9]. Apolloni et al [12] present BICA (Boolean independent components analysis) for extracting bits from the original features. It looks for Boolean independent variables along with minimal joint entropy and consistent assignments and produces a vector of Boolean variables whose assignments reflect the relevant features of the original data set, under the consistency control that the same assignment is not generated by data set having different classification labels.…”
Section: Literature Reviewmentioning
confidence: 99%