Improving nature-inspired algorithms for feature selection

Al-Thanoon, Niam Abdulmunim; Qasim, Omar Saber; Algamal, Zakariya Yahya

doi:10.1007/s12652-021-03136-6

Cited by 7 publications

(4 citation statements)

References 49 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A bat-inspired algorithm is based on the ability of bats to locate their prey using echos. The bats have the unique characteristic of releasing a loud sound, and that sound's echo helps them find their prey [ 67 ]. The values of velocity, frequency, and position of the bat are updated using the importance of local and global minima and maxima, which helped locate nearby prey.…”

Section: Related Workmentioning

confidence: 99%

A Systematic Review on Metaheuristic Optimization Techniques for Feature Selections in Disease Diagnosis: Open Issues and Challenges

Kaur¹,

Kumar

Koul

et al. 2022

Arch Computat Methods Eng

View full text Add to dashboard Cite

There is a need for some techniques to solve various problems in today’s computing world. Metaheuristic algorithms are one of the techniques which are capable of providing practical solutions to such issues. Due to their efficiency, metaheuristic algorithms are now used in healthcare data to diagnose diseases practically and with better results than traditional methods. In this study, an efficient search has been performed where 173 papers from different research databases such as Scopus, Web of Science, PubMed, PsycINFO, and others have been considered impactful in diagnosing the diseases using metaheuristic techniques. Ten metaheuristic techniques have been studied, which include spider monkey, shuffled frog leaping algorithm, cuckoo search algorithm, ant lion technique of optimization, lion optimization technique, moth flame technique, bat-inspired algorithm, grey wolf algorithm, whale optimization, and dragonfly technique of optimization for selecting and optimizing the features to predict heart disease, Alzheimer's disease, brain disorder, diabetes, chronic disease features, liver disease, covid-19, etc. Besides, the framework has also been shown to provide information on various phases behind the execution of metaheuristic techniques to predict diseases. The study’s primary goal is to present the contribution of the researchers by demonstrating their methodology to predict diseases using the metaheuristic techniques mentioned above. Later, their work has also been compared and evaluated using accuracy, precision, F1 score, error rate, sensitivity, specificity, an area under a curve, etc., to help the researchers to choose the right field and methods for predicting the diseases in the future.

show abstract

Section: Related Workmentioning

confidence: 99%

A Systematic Review on Metaheuristic Optimization Techniques for Feature Selections in Disease Diagnosis: Open Issues and Challenges

Kaur¹,

Kumar

Koul

et al. 2022

Arch Computat Methods Eng

View full text Add to dashboard Cite

show abstract

“…computation time is usually longer than a normal machine learning algorithm. It performs with noise data such as data with lots of highly correlated features [40]. Show in Figure 3.…”

Section: 𝑓 (𝑥) = 𝑠𝑖𝑛 (𝑤𝑇 𝑥 + 𝑏) (4)mentioning

confidence: 99%

“…The number of neighbors to be considered for polling is defined by the value of K, which is a positive integer. The value of K in this analysis is 11, which was chosen using the trial and error method [40]. KNN classifier shown in Figure 4.…”

Section: K-nearest Neighbors (K-nn)mentioning

confidence: 99%

Alzheimer’s disease prediction using three machine learning methods

Ahmed

Kadhem

2022

IJEECS

View full text Add to dashboard Cite

Alzheimer's disease (AD) is the most common incurable neurodegenerative illness, a term that encompasses memory loss as well as other cognitive abilities. The purpose of the study is using precise early-stage gene expression data from blood generated from a clinical Alzheimer's dataset, the goal was to construct a classification model that might predict the early stages of Alzheimer's disease. Using information gain (IG), a selection of characteristics was chosen to provide substantial information for distinguishing between normal control (NC) and early-stage AD participants. The data was divided into various sizes; three distinct machine learning (ML) algorithms were used to generate the classification models: support vector machine (SVM), Naïve Bayes (NB), and k-nearest neighbors (K-NN). Using the WEKA software tool and a variety of model performance measures, the capacity of the algorithms to effectively predict cognitive impairment status was compared and tested. The current findings reveal that an SVM-based classification model can accurately differentiate cognitively impaired Alzheimer's patients from normal healthy people with 96.6% accuracy. As discovered and validated a gene expression pattern in the blood that accurately distinguishes Alzheimer's patients and cognitively healthy controls, demonstrating that changes specific to AD can be detected far from the disease's core site.

show abstract

“…where t is the number of iterations, w ∈ [0, 1] is the inertia weight, c 1 and c 2 are learning factors; rand 1 and rand 2 are random numbers selected between 0 and 1 [12], [13].…”

Section: Particle Swarm Optimizationmentioning

confidence: 99%

Shooting swarm algorithm for solving two-point boundary value problems

Altamir

Kahya

Aladool

2022

IJEECS

View full text Add to dashboard Cite

Boundary value problems (BVPs) are solved using the more detailed swarm algorithm (SA) based on particle swarm optimization (PSO) and firefly algorithm (FA). In the field of optimization techniques, both PSO and FA have good features to solve many problems in applied mathematics. Due to the sensitivity of the use of the controversial shooting method for solving BVPs, which can not able to reach the exact solution oftentimes. A shooting Swarm algorithm (SSA) is proposed based on PSO and FA. Several BVPs including stiff BVPs were principally used to investigate the SSA. The numerical experiments and analyses revealed that the algorithm was able to overcome the shooing method drawbacks. On another hand, the proposed method that is based on FA significantly reduces the number of iterations required for solving BVPs, because of its flexible properties in the exploration and exploitation phases, and it is in good agreement with the exact solution of BVPs. The SSA was investigated to solve stiff BVPs and Its efficacy has been proven with the accurate solutions.

show abstract

Improving nature-inspired algorithms for feature selection

Cited by 7 publications

References 49 publications

A Systematic Review on Metaheuristic Optimization Techniques for Feature Selections in Disease Diagnosis: Open Issues and Challenges

A Systematic Review on Metaheuristic Optimization Techniques for Feature Selections in Disease Diagnosis: Open Issues and Challenges

Alzheimer’s disease prediction using three machine learning methods

Shooting swarm algorithm for solving two-point boundary value problems

Contact Info

Product

Resources

About