Innovative Feature Selection Method Based on Hybrid Sine Cosine and Dipper Throated Optimization Algorithms

Abdelaziz A. Abdelhamid; El Sayed M. El-kenawy; Abdelhameed Ibrahim; Marwa M. Eid; Doaa Sami Khafaga; Amel Ali Alhussan; Seyedali Mirjalili; Nima Khodadadi; Wei Hong Lim; Mahmoud Y. Shams

doi:10.1109/ACCESS.2023.3298955

Innovative Feature Selection Method Based on Hybrid Sine Cosine and Dipper Throated Optimization Algorithms

Abdelaziz A. Abdelhamid, El Sayed M. El-kenawy, Abdelhameed Ibrahim, Marwa M. Eid, Doaa Sami Khafaga, Amel Ali Alhussan, Seyedali Mirjalili, Nima Khodadadi, Wei Hong Lim, Mahmoud Y. Shams

Artificial Intelligence Research and Optimization

Research output: Contribution to journal › Article › peer-review

1 Citation (Scopus)

Abstract

<italic>Introduction</italic>: In pattern recognition and data mining, feature selection is one of the most crucial tasks. To increase the efficacy of classification algorithms, it is necessary to identify the most relevant subset of features in a given domain. This means that the feature selection challenge can be seen as an optimization problem, and thus meta-heuristic techniques can be utilized to find a solution. <italic>Methodology</italic>: In this work, we propose a novel hybrid binary meta-heuristic algorithm to solve the feature selection problem by combining two algorithms: Dipper Throated Optimization (DTO) and Sine Cosine (SC) algorithm. The new algorithm is referred to as bSCWDTO. We employed the sine cosine algorithm to improve the exploration process and ensure the optimization algorithm converges quickly and accurately. Thirty datasets from the University of California Irvine (UCI) machine learning repository are used to evaluate the robustness and stability of the proposed bSCWDTO algorithm. In addition, the K-Nearest Neighbor (KNN) classifier is used to measure the selected features’ effectiveness in classification problems. <italic>Results</italic>: The achieved results demonstrate the algorithm’s superiority over ten state-of-the-art optimization methods, including the original DTO and SC, Particle Swarm Optimization (PSO), Whale Optimization Algorithm (WOA), Grey Wolf Optimization (GWO), Multiverse Optimization (MVO), Satin Bowerbird Optimizer (SBO), Genetic Algorithm (GA), the hybrid of GWO and GA, and Firefly Algorithm (FA). Moreover, Wilcoxon’s rank-sum test was performed at the 0.05 significance level to study the statistical difference between the proposed method and the alternative feature selection methods. <italic>Conclusion</italic>: These results emphasized the proposed feature selection method’s significance, superiority, and statistical difference.

Original language	English
Pages (from-to)	1
Number of pages	1
Journal	IEEE Access
DOIs	https://doi.org/10.1109/ACCESS.2023.3298955
Publication status	Published - 2023

Keywords

Classification algorithms
Dipper throated optimization algorithm
Feature extraction
Feature selection
Genetic algorithms
Machine learning
Mathematical models
Meta-heuristic optimization
Metaheuristics
Optimization
Sine cosine optimization algorithm

Access to Document

10.1109/ACCESS.2023.3298955

Cite this

@article{adadab37fa47407dba03f77e2a72e119,

title = "Innovative Feature Selection Method Based on Hybrid Sine Cosine and Dipper Throated Optimization Algorithms",

abstract = "Introduction: In pattern recognition and data mining, feature selection is one of the most crucial tasks. To increase the efficacy of classification algorithms, it is necessary to identify the most relevant subset of features in a given domain. This means that the feature selection challenge can be seen as an optimization problem, and thus meta-heuristic techniques can be utilized to find a solution. Methodology: In this work, we propose a novel hybrid binary meta-heuristic algorithm to solve the feature selection problem by combining two algorithms: Dipper Throated Optimization (DTO) and Sine Cosine (SC) algorithm. The new algorithm is referred to as bSCWDTO. We employed the sine cosine algorithm to improve the exploration process and ensure the optimization algorithm converges quickly and accurately. Thirty datasets from the University of California Irvine (UCI) machine learning repository are used to evaluate the robustness and stability of the proposed bSCWDTO algorithm. In addition, the K-Nearest Neighbor (KNN) classifier is used to measure the selected features{\textquoteright} effectiveness in classification problems. Results: The achieved results demonstrate the algorithm{\textquoteright}s superiority over ten state-of-the-art optimization methods, including the original DTO and SC, Particle Swarm Optimization (PSO), Whale Optimization Algorithm (WOA), Grey Wolf Optimization (GWO), Multiverse Optimization (MVO), Satin Bowerbird Optimizer (SBO), Genetic Algorithm (GA), the hybrid of GWO and GA, and Firefly Algorithm (FA). Moreover, Wilcoxon{\textquoteright}s rank-sum test was performed at the 0.05 significance level to study the statistical difference between the proposed method and the alternative feature selection methods. Conclusion: These results emphasized the proposed feature selection method{\textquoteright}s significance, superiority, and statistical difference.",

keywords = "Classification algorithms, Dipper throated optimization algorithm, Feature extraction, Feature selection, Genetic algorithms, Machine learning, Mathematical models, Meta-heuristic optimization, Metaheuristics, Optimization, Sine cosine optimization algorithm",

author = "Abdelhamid, {Abdelaziz A.} and El-kenawy, {El Sayed M.} and Abdelhameed Ibrahim and Eid, {Marwa M.} and Khafaga, {Doaa Sami} and Alhussan, {Amel Ali} and Seyedali Mirjalili and Nima Khodadadi and Lim, {Wei Hong} and Shams, {Mahmoud Y.}",

note = "Publisher Copyright: Author",

year = "2023",

doi = "10.1109/ACCESS.2023.3298955",

language = "English",

pages = "1",

journal = "IEEE Access",

issn = "2169-3536",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - JOUR

T1 - Innovative Feature Selection Method Based on Hybrid Sine Cosine and Dipper Throated Optimization Algorithms

AU - Abdelhamid, Abdelaziz A.

AU - El-kenawy, El Sayed M.

AU - Ibrahim, Abdelhameed

AU - Eid, Marwa M.

AU - Khafaga, Doaa Sami

AU - Alhussan, Amel Ali

AU - Mirjalili, Seyedali

AU - Khodadadi, Nima

AU - Lim, Wei Hong

AU - Shams, Mahmoud Y.

N1 - Publisher Copyright: Author

PY - 2023

Y1 - 2023

N2 - Introduction: In pattern recognition and data mining, feature selection is one of the most crucial tasks. To increase the efficacy of classification algorithms, it is necessary to identify the most relevant subset of features in a given domain. This means that the feature selection challenge can be seen as an optimization problem, and thus meta-heuristic techniques can be utilized to find a solution. Methodology: In this work, we propose a novel hybrid binary meta-heuristic algorithm to solve the feature selection problem by combining two algorithms: Dipper Throated Optimization (DTO) and Sine Cosine (SC) algorithm. The new algorithm is referred to as bSCWDTO. We employed the sine cosine algorithm to improve the exploration process and ensure the optimization algorithm converges quickly and accurately. Thirty datasets from the University of California Irvine (UCI) machine learning repository are used to evaluate the robustness and stability of the proposed bSCWDTO algorithm. In addition, the K-Nearest Neighbor (KNN) classifier is used to measure the selected features’ effectiveness in classification problems. Results: The achieved results demonstrate the algorithm’s superiority over ten state-of-the-art optimization methods, including the original DTO and SC, Particle Swarm Optimization (PSO), Whale Optimization Algorithm (WOA), Grey Wolf Optimization (GWO), Multiverse Optimization (MVO), Satin Bowerbird Optimizer (SBO), Genetic Algorithm (GA), the hybrid of GWO and GA, and Firefly Algorithm (FA). Moreover, Wilcoxon’s rank-sum test was performed at the 0.05 significance level to study the statistical difference between the proposed method and the alternative feature selection methods. Conclusion: These results emphasized the proposed feature selection method’s significance, superiority, and statistical difference.

AB - Introduction: In pattern recognition and data mining, feature selection is one of the most crucial tasks. To increase the efficacy of classification algorithms, it is necessary to identify the most relevant subset of features in a given domain. This means that the feature selection challenge can be seen as an optimization problem, and thus meta-heuristic techniques can be utilized to find a solution. Methodology: In this work, we propose a novel hybrid binary meta-heuristic algorithm to solve the feature selection problem by combining two algorithms: Dipper Throated Optimization (DTO) and Sine Cosine (SC) algorithm. The new algorithm is referred to as bSCWDTO. We employed the sine cosine algorithm to improve the exploration process and ensure the optimization algorithm converges quickly and accurately. Thirty datasets from the University of California Irvine (UCI) machine learning repository are used to evaluate the robustness and stability of the proposed bSCWDTO algorithm. In addition, the K-Nearest Neighbor (KNN) classifier is used to measure the selected features’ effectiveness in classification problems. Results: The achieved results demonstrate the algorithm’s superiority over ten state-of-the-art optimization methods, including the original DTO and SC, Particle Swarm Optimization (PSO), Whale Optimization Algorithm (WOA), Grey Wolf Optimization (GWO), Multiverse Optimization (MVO), Satin Bowerbird Optimizer (SBO), Genetic Algorithm (GA), the hybrid of GWO and GA, and Firefly Algorithm (FA). Moreover, Wilcoxon’s rank-sum test was performed at the 0.05 significance level to study the statistical difference between the proposed method and the alternative feature selection methods. Conclusion: These results emphasized the proposed feature selection method’s significance, superiority, and statistical difference.

KW - Classification algorithms

KW - Dipper throated optimization algorithm

KW - Feature extraction

KW - Feature selection

KW - Genetic algorithms

KW - Machine learning

KW - Mathematical models

KW - Meta-heuristic optimization

KW - Metaheuristics

KW - Optimization

KW - Sine cosine optimization algorithm

UR - http://www.scopus.com/inward/record.url?scp=85165925797&partnerID=8YFLogxK

U2 - 10.1109/ACCESS.2023.3298955

DO - 10.1109/ACCESS.2023.3298955

M3 - Article

AN - SCOPUS:85165925797

SN - 2169-3536

SP - 1

JO - IEEE Access

JF - IEEE Access

ER -

Innovative Feature Selection Method Based on Hybrid Sine Cosine and Dipper Throated Optimization Algorithms

Abstract

Keywords

Access to Document

Other files and links

Fingerprint

Cite this