2012 IEEE Congress on Evolutionary Computation 2012
DOI: 10.1109/cec.2012.6256617
|View full text |Cite
|
Sign up to set email alerts
|

New fitness functions in binary particle swarm optimisation for feature selection

Abstract: Feature selection is an important data preprocessing technique in classification problems. This paper proposes two new fitness functions in binary particle swarm optimisation (BPSO) for feature selection to choose a small number of features and achieve high classification accuracy. In the first fitness function, the relative importance of classification performance and the number of features are balanced by using a linearly increasing weight in the evolutionary process. The second is a two-stage fitness functi… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
2

Citation Types

0
7
0

Year Published

2019
2019
2024
2024

Publication Types

Select...
7
2
1

Relationship

0
10

Authors

Journals

citations
Cited by 21 publications
(7 citation statements)
references
References 24 publications
0
7
0
Order By: Relevance
“…PCA and PSO are employed as a dimensionality reduction technique for feature selection. It is inferred that PSO has shown promising results in extracting a proper subset of features [9][10][11]. Compared to other evolutionary algorithms PSO is computationally less expensive and converges more quickly [12].…”
Section: Introductionmentioning
confidence: 99%
“…PCA and PSO are employed as a dimensionality reduction technique for feature selection. It is inferred that PSO has shown promising results in extracting a proper subset of features [9][10][11]. Compared to other evolutionary algorithms PSO is computationally less expensive and converges more quickly [12].…”
Section: Introductionmentioning
confidence: 99%
“…In this, the important objective function is the classification error. However, more than one objective functions based solely on classification error are required to guide the BPSO algorithm toward selecting small and low-dimensional inputs [11]. This paper proposes the application of a multi-objective feature selection function based on the minimum classification error with minimum size of feature-subset or the highest classification accuracy with the least number of input featuresubset.…”
Section: Introductionmentioning
confidence: 99%
“…The work conducted by the authors in reference 15 involved the modification of the continuous Particle Swarm Optimization(PSO) algorithm to a binary PSO algorithm for the purpose of feature selection 13 . In order to enhance the accuracy of classification, the research conducted in reference 16 employed a combination of Particle Swarm Optimization(PSO) and Linear Discriminant Analysis(LDA) 16 .…”
mentioning
confidence: 99%