Metaheuristics for optimal feature selection in high-dimensional datasets

Segera, Davies; Mbuthia, Mwangi; Nyete, Abraham

doi:10.1016/b978-0-323-91781-0.00013-2

Cited by 1 publication

(6 citation statements)

References 45 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…2. The subset Φ will thus contain the features with the minimum of redundancy and of noisy as well as the maximum of relevance [1,5,14,47,48].…”

Section: Feature Selection Overviewmentioning

confidence: 99%

“…Thus, an efficient metaheuristic for the resolution of the NP-Hard optimization problems of feature selection, will browse the vertices of the hypercube ℬ 𝑑 by exploration and exploitation phases in a reasonable time in search of a good solution close to the optimal solution. The natureinspired and population-based metaheuristics are the most likely to grant us the benefits of feature selection [1,47].…”

Section: Mathematical Theory Of the Feature Selectionmentioning

confidence: 99%

“…The increase of irrelevant and redundant features composing high-dimensional data complicates the design of systems based on deep learning and favors the curse of dimension [1]. This observation does not spare any scientific field: cybersecurity, medicine, economy, chemistry, physics, etc.…”

Section: Introductionmentioning

confidence: 99%

“…Feature selections are classified into four main methods: filter, wrapper, embedded and hybridized [1,[3][4][5]. Although more computationally expensive, the most efficient method for a deep learning classifier trained by a high-dimensional data is the wrapper method [1] and it is the one that we exploit in this article.…”

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

BHHO-EAS metaheuristic applied to the NP-Hard wrapper feature selection multi-objective optimization problem

SASSI,

CHELOUAH

2024

Preprint

View full text Add to dashboard Cite

Faced with the increase in high-dimensional Big Data creating more volume and complexity, the feature selection process became an essential phase in the preprocessing workflow upstream of the design of systems based on deep learning. This paper is a concrete and first application of the new metaheuristic Harris Hawk Optimization Encirclement-Attack-Synergy (HHO-EAS) in solving the NP-Hard wrapper feature selection multi-objective optimization problem. This problem combines two contradictory objectives: maximizing the accuracy of a classifier while minimizing the number of the most relevant and non-redundant selected features. To do this we hybridized HHO-EAS to create the new metaheuristic Binary HHO-EAS (BHHO-EAS). We combined HHO-EAS to the sixteen transfer functions most used in the literature structured in a balanced way among the four main categories including S-Shaped, V-Shaped, Q-Shaped and U-Shaped. This wide range of transfer function allows us to analyze the evolution of BHHO-EAS’s skills according to the assigned transfer function and to determine which of them offer the best performances. We applied wrapper feature selection to the well-known NSL-KDD dataset with the deep learning Multi Layer Perceptron (MLP) classifier. We put BHHO-EAS in competition with three other well-known population based binary metaheuristics, BPSO, BBA and BHHO. The analysis of the experimental results, compared to the three other binary metaheuristics, demonstrated that BHHO-EAS obtained the best performance on 100% of the transfer functions. This is more particularly highlighted by the U-Shaped transfer functions, which give an acceptable compromise for the two objectives of the problem with an average accuracy of 96,4% and an average size of selected features of 20.

show abstract

“…2. The subset Φ will thus contain the features with the minimum of redundancy and of noisy as well as the maximum of relevance [1,5,14,47,48].…”

Section: Feature Selection Overviewmentioning

confidence: 99%

Section: Mathematical Theory Of the Feature Selectionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

BHHO-EAS metaheuristic applied to the NP-Hard wrapper feature selection multi-objective optimization problem

SASSI,

CHELOUAH

2024

Preprint

View full text Add to dashboard Cite

show abstract

Metaheuristics for optimal feature selection in high-dimensional datasets

Cited by 1 publication

References 45 publications

BHHO-EAS metaheuristic applied to the NP-Hard wrapper feature selection multi-objective optimization problem

BHHO-EAS metaheuristic applied to the NP-Hard wrapper feature selection multi-objective optimization problem

Contact Info

Product

Resources

About