An improved binary manta ray foraging optimization algorithm based feature selection and random forest classifier for network intrusion detection

Hassan, Ibrahim Hayatu; Mohammed, Abdullahi; Masama, Mansur Aliyu; Ali, Yusuf Sahabi; Abdulrahim, Abdulrazaq

doi:10.1016/j.iswa.2022.200114

Cited by 26 publications

(14 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Manta‐ray foraging optimization (MRFO) is a nature‐inspired methodology based on manta‐ray foraging behavior and is noted for its efficient foraging strategies 51 . The MRFO uses a population‐based method that represents potential solutions as rays 52 . These rays scour the environment, replicating manta‐ray behavior by looking for food, avoiding risks, and maintaining social connections.…”

Section: Methodsmentioning

confidence: 99%

See 1 more Smart Citation

Deep learning network selection and optimized information fusion for enhanced COVID‐19 detection

Ali,

Zafar,

Tanveer

et al. 2023

Int J Imaging Syst Tech

View full text Add to dashboard Cite

This study proposes a wrapper‐based technique to improve the classification performance of chest infection (including COVID‐19) detection using X‐rays. Deep features were extracted using pretrained deep learning models. Ten optimization techniques, including poor and rich optimization, path finder algorithm, Henry gas solubility optimization, Harris hawks optimization, atom search optimization, manta‐ray foraging optimization, equilibrium optimizer, slime mold algorithm, generalized normal distribution optimization, and marine predator algorithm, were used to determine the optimal features using a support vector machine. Moreover, a network selection technique was used to select the deep learning models. An online chest infection detection X‐ray scan dataset was used to validate the proposed approach. The results suggest that the proposed wrapper‐based automatic deep learning network selection and feature optimization framework has a high classification rate of 97.7%. The comparative analysis further validates the credibility of the framework in COVID‐19 and other chest infection classifications, suggesting that the proposed approach can help doctors in clinical practice.

show abstract

Section: Methodsmentioning

confidence: 99%

“…51 The MRFO uses a population-based method that represents potential solutions as rays. 52 These rays scour the environment, replicating manta-ray behavior by looking for food, avoiding risks, and maintaining social connections. The system dynamically modifies the ray motion based on individual and community knowledge.…”

Section: Manta-ray Foraging Optimizationmentioning

confidence: 99%

Deep learning network selection and optimized information fusion for enhanced COVID‐19 detection

Ali,

Zafar,

Tanveer

et al. 2023

Int J Imaging Syst Tech

View full text Add to dashboard Cite

show abstract

“…Once these issues are resolved, the features selected by the algorithm can be used to improve training time and accuracy of ML models for prediction of the presence of cancerous tumors in the patient. [10].…”

Section: Implications Of Researchmentioning

confidence: 99%

“…presence of cancerous tumors in the patient. [10]. This document analyzes the pre existing algorithms developed in the space of Feature Selection using the MRFO algorithm in the GEM dataset.…”

mentioning

confidence: 99%

Feature Selection in MicroArray Datasets using Manta Ray Foraging Optimization Technique

Tayal¹,

Neelakantan²,

Bhargava³

2023

Proceedings of the International Conference on Application of AI and Statistical Decision Making for the Business World, ICASDM

View full text Add to dashboard Cite

In this document, we apply the Manta Ray Foraging Optimization technique for Feature Selection in the genetic dataset to identify the relevant features from a high dimensional feature space. MRFO is one of the recent meta-heuristic optimization techniques which has been used for Feature Selection. presence of cancerous tumors in the patient. [10]. This document analyzes the pre existing algorithms developed in the space of Feature Selection using the MRFO algorithm in the GEM dataset. The MRFO method uses three unique search techniques in three different ways. The local search ability of the algorithm is highly aided by the chain foraging behavior; the global search ability is determined by the manta ray cyclone foraging behavior; and the local search ability and convergence rate are greatly improved by the somersault foraging behavior. This document, two separate learning classifiers were used: K-NearestNeighbors (KNN) classifier and the Random Forest Classifier were used for calculating the fitness

show abstract

“…However, high dimensionality poses numerous challenges, such as increased computational complexity, overfitting, and reduced interpretability of the resulting models. To address these issues, feature selection techniques have been developed to identify the most relevant variables, reduce dimensionality, and enhance model performance [2].…”

Section: Introductionmentioning

confidence: 99%

BukaGini: A Stability-Aware Gini Index Feature Selection Algorithm for Robust Model Performance

Bouke

Abdullah

Frnda³

et al. 2023

IEEE Access

View full text Add to dashboard Cite

Feature interaction is a vital aspect of Machine Learning (ML) algorithms, and gaining a deep understanding of these interactions can significantly enhance model performance. This paper introduces the BukaGini algorithm, an innovative and robust approach for feature interaction analysis that capitalizes on the Gini impurity index. By exploiting the unique properties of the BukaGini index, our proposed algorithm effectively captures both linear and nonlinear feature interactions, providing a richer and more comprehensive representation of the underlying data. We thoroughly evaluate the BukaGini algorithm against traditional Gini index-based methods on various real-world datasets. These datasets include the High School Students' Performance (HSSP) dataset, which examines factors affecting student performance; Cancer Data, which focuses on identifying cancer types based on gene expression; Spambase, which targets spam email classification; and the UNSW-NB15 dataset, which addresses network intrusion detection. Our experimental results demonstrate that the BukaGini algorithm consistently outperforms traditional Gini index-based methods in terms of accuracy. Across the tested datasets, the BukaGini algorithm achieves improvements ranging from 0.32% to 2.50%, underscoring its effectiveness in handling diverse data types and problem domains. This performance gain highlights the potential of the BukaGini algorithm as a valuable tool for feature interaction analysis in various ML applications.INDEX TERMS BukaGini algorithm, Gini index, ensemble learning, feature interaction analysis, data mining.

show abstract

An improved binary manta ray foraging optimization algorithm based feature selection and random forest classifier for network intrusion detection

Cited by 26 publications

References 23 publications

Deep learning network selection and optimized information fusion for enhanced COVID‐19 detection

Deep learning network selection and optimized information fusion for enhanced COVID‐19 detection

Feature Selection in MicroArray Datasets using Manta Ray Foraging Optimization Technique

BukaGini: A Stability-Aware Gini Index Feature Selection Algorithm for Robust Model Performance

Contact Info

Product

Resources

About