Extended particle swarm optimization for feature selection of high‐dimensional biomedical data

Abstract

This paper proposes a novel Extended Particle Swarm Optimization model (EPSO) that potentially enhances the search process of PSO for optimization problem. Evidently, gene expression profiles are significantly important measurement factor in molecular biology that is used in medical diagnosis of cancer types. The challenge to certain classification methodologies for gene expression profiles lies in the thousands of features recorded for each sample. A modified Wrapper feature selection model is applied with the aim of addressing the gene classification challenge by replacing its randomness approach with EPSO and PSO, respectively. EPSO is initializing the random size of the population and dividing them into two groups in order to promote the exploration and reduce the probability of falling in stagnation. Experimentally, EPSO has required less processing time to select the optimal features (average of 62.14 s) than PSO (average of 95.72 s). Furthermore, EPSO accuracy has provided better classification results

Fractal feature selection model for enhancing high-dimensional biological problems

“…Al-Shammary et al [ 2 ] introduced the extended particle swarm optimization (EPSO) model, potentially improving the PSO search process for optimization problems. The model is applied to gene expression profiles, important molecular biology measurement factors used in cancer diagnosis.…”

“…It identifies and diagnoses cancer by examining gene activity and cellular function. Gene expression profiling (GEP) is a helpful description used in bioinformatics to measure the activity of thousands of genes simultaneously, providing a comprehensive picture of cellular function in a particular biological sample [ 2 ]. However, this wealth of molecular information presents a unique challenge and opportunity for the field of artificial intelligence [ 3 ].…”

“…The search space, usually between 0 and 1, can lead to a stagnation scenario that hinders the comprehensive exploration of optimal feature subsets [ 23 ]. Integration of metaheuristics : A promising way to overcome these limitations is to integrate metaheuristics into different aspects of the system [ 2 , 24 ]. The strategic application of metaheuristics has led to tangible improvements that address the challenges of unstable performance and expand the search space for more robust exploration.…”

Enhanced PSO Algorithm for Detecting DRDoS Attacks on LDAP Servers

“…With the increasing number and diversity of datasets, it becomes imperative to systematically reduce them. Therefore, feature selection aims to pick certain essential attributes from the initial feature set that will increase the effectiveness of a predictive model and lower the computational cost of modeling [19]- [21].…”

“…The birds move from one location to another in search of food, and the birds can smell food wherever it is available. The bird knows its surroundings and uses them to locate and manage food resources [22]. The global optimization approaches are used to calculate the learning approach from the animal's behavior, where the swarm or crowd will be known as a particle [23,24].…”