% IMPORTANT: The following is UTF-8 encoded. This means that in the presence
% of non-ASCII characters, it will not work with BibTeX 0.99 or older.
% Instead, you should use an up-to-date BibTeX implementation like “bibtex8” or
% “biber”.
@ARTICLE{Alia:894810,
author = {Alia, Ahmed and Taweel, Adel},
title = {{E}nhanced {B}inary {C}uckoo {S}earch {W}ith {F}requent
{V}alues and {R}ough {S}et {T}heory for {F}eature
{S}election},
journal = {IEEE access},
volume = {9},
issn = {2169-3536},
address = {New York, NY},
publisher = {IEEE},
reportid = {FZJ-2021-03405},
pages = {119430 - 119453},
year = {2021},
abstract = {Redundant and irrelevant features in datasets decrease
classification accuracy, and increase computational time of
classification algorithms, overfitting problem and
complexity of the underlying classification model. Feature
selection is a preprocessing technique used in
classification algorithms to improve the selection of
relevant features. Several approaches that combine Rough Set
Theory (RST) with Nature Inspired Algorithms (NIAs) have
been used successfully for feature selection. However, due
to the inherit limitations of RST for some data types and
the inefficient convergence of NIAs for high dimensional
datasets, these approaches have mainly focused on a specific
type of low dimensional nominal dataset. This paper proposes
a new filter feature selection approach based on Binary
Cuckoo Search (BCS) and RST, which is more efficient for low
and high dimensional nominal, mixed and numerical datasets.
It enhances BCS by developing a new initialization and
global update mechanisms to increase the efficiency of
convergence for high dimensional datasets. It also develops
a more efficient objective function for numerical, mixed and
nominal datasets. The proposed approach was validated on 16
benchmark datasets; 4 nominal, 4 mixed and 8 numerical drawn
from the UCI repository. It was also evaluated against
standard BCS; five NIAs with fuzzy RST approaches; two
popular traditional FS approaches; and multi objective
evolutionary, Genetic, and Particle Swarm Optimization (PSO)
algorithms. Decision tree and Naive Bayes algorithms were
used to measure the classification performance of the
proposed approach. The results show that the proposed
approach achieved improved classification accuracy while
minimizing the number of features compared to other
state-of-the-art methods.},
cin = {IAS-7},
ddc = {621.3},
cid = {I:(DE-Juel1)IAS-7-20180321},
pnm = {5111 - Domain-Specific Simulation $\&$ Data Life Cycle Labs
(SDLs) and Research Groups (POF4-511)},
pid = {G:(DE-HGF)POF4-5111},
typ = {PUB:(DE-HGF)16},
UT = {WOS:000692224900001},
doi = {10.1109/ACCESS.2021.3107901},
url = {https://juser.fz-juelich.de/record/894810},
}