Hybrid Reptile Search Algorithm and Remora Optimization Algorithm for Optimization Tasks and Data Clustering

Khaled H Almotairi,Laith Abualigah

doi:10.3390/sym14030458

Khaled H Almotairi, Laith Abualigah

Open Access

https://doi.org/10.3390/sym14030458

Copy DOI

Abstract

Data clustering is a complex data mining problem that clusters a massive amount of data objects into a predefined number of clusters; in other words, it finds symmetric and asymmetric objects. Various optimization methods have been used to solve different machine learning problems. They usually suffer from local optimal problems and unbalance between the search mechanisms. This paper proposes a novel hybrid optimization method for solving various optimization problems. The proposed method is called HRSA, which combines the original Reptile Search Algorithm (RSA) and Remora Optimization Algorithm (ROA) and handles these mechanisms’ search processes by a novel transition method. The proposed HRSA method aims to avoid the main weaknesses raised by the original methods and find better solutions. The proposed HRSA is tested on solving various complicated optimization problems—twenty-three benchmark test functions and eight data clustering problems. The obtained results illustrate that the proposed HRSA method performs significantly better than the original and comparative state-of-the-art methods. The proposed method overwhelmed all the comparative methods according to the mathematical problems. It obtained promising results in solving the clustering problems. Thus, HRSA has a remarkable efficacy when employed for various clustering problems.

Highlights

Unsupervised learning methods are instrumental in machine learning because they may explore data without any prior knowledge of them, i.e., there are no labels linked with the data [1]
Various optimization methods have been employed in the literature to solve different machine learning problems, especially clustering problems
Optimization methods usually suffer from optimal local problems and unbalance between the search mechanisms

Summary

Introduction

Unsupervised learning methods are instrumental in machine learning because they may explore data without any prior knowledge of them, i.e., there are no labels linked with the data [1]. These algorithms try to represent the data’s underlying mechanism or pattern, which may be helpful for things such as decision making and forecasting future inputs. Algorithms for clustering have been utilized in a wide range of applications They are used in biology to extract interesting patterns from gene expression [5,6]. We present the original Reptile Search Algorithm (RSA) and its procedure. Crocodiles engage in two movements when encircling: high walking and belly walking, according to their encircling behavior [29]

Methods

Results

Conclusion