Advances in Parameter-Tuning Techniques for Metaheuristic Algorithms

A special issue of Axioms (ISSN 2075-1680). This special issue belongs to the section "Mathematical Analysis".

Deadline for manuscript submissions: 30 October 2024 | Viewed by 574

Special Issue Editor


E-Mail Website
Guest Editor
Department of Computer Science & Engineering, University of Ioannina, 45110 Ioannina, Greece
Interests: parameter tuning; computational optimization; metaheuristic algorithms; machine learning

Special Issue Information

Dear Colleagues,

Metaheuristic algorithms are advanced computational strategies considered state-of-the-art solvers often used in complex computational optimization problems where traditional methods are inefficient or infeasible. These algorithms are particularly beneficial due to their flexibility, robustness, and ability to provide sub-optimal solutions even in complex and non-linear search spaces in a reasonable time. However, their performance is strongly correlated with proper parameterization. Optimal tuning is a crucial aspect and can have a significant performance impact on their applications as it controls the balance between exploration (global search) and exploitation (local search) in the search space. Fine-tuning can result in a local optimal or inefficient search. Therefore, ensuring proper tuning/control is a fundamental step in their applications to the corresponding problem in order to deliver efficient, accurate, and reliable solutions.

This Special Issue is devoted to state-of-the-art research in parameter-tuning techniques for metaheuristic algorithms and their application to various problems. Thus, the Guest Editors would like to provide an opportunity to present recent developments in the areas mentioned above, and the topics of this Special Issue include, but are not limited to, the following:

Parameter tuning, parameter control, offline parameter tuning, online parameter tuning, computational optimization, metaheuristic algorithms, swarm intelligence, population-based, genetic algorithms, and applications in real-world problems or benchmark functions.

This Special Issue welcomes research exploring further topics in addition to the abovementioned. 

We hope this initiative will attract researchers specializing in the above areas of interest and encourage them to submit their novel research to this Special Issue.

Dr. Vasileios A. Tatsis
Guest Editor

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Axioms is an international peer-reviewed open access monthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 2400 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

Keywords

  • computational optimization
  • metaheuristic algorithms
  • parameter tuning
  • swarm intelligence
  • real-world applications

Published Papers (1 paper)

Order results
Result details
Select all
Export citation of selected articles as:

Research

31 pages, 1604 KiB  
Article
Respiratory Condition Detection Using Audio Analysis and Convolutional Neural Networks Optimized by Modified Metaheuristics
by Nebojsa Bacanin, Luka Jovanovic, Ruxandra Stoean, Catalin Stoean, Miodrag Zivkovic, Milos Antonijevic and Milos Dobrojevic
Axioms 2024, 13(5), 335; https://0-doi-org.brum.beds.ac.uk/10.3390/axioms13050335 - 18 May 2024
Viewed by 193
Abstract
Respiratory conditions have been a focal point in recent medical studies. Early detection and timely treatment are crucial factors in improving patient outcomes for any medical condition. Traditionally, doctors diagnose respiratory conditions through an investigation process that involves listening to the patient’s lungs. [...] Read more.
Respiratory conditions have been a focal point in recent medical studies. Early detection and timely treatment are crucial factors in improving patient outcomes for any medical condition. Traditionally, doctors diagnose respiratory conditions through an investigation process that involves listening to the patient’s lungs. This study explores the potential of combining audio analysis with convolutional neural networks to detect respiratory conditions in patients. Given the significant impact of proper hyperparameter selection on network performance, contemporary optimizers are employed to enhance efficiency. Moreover, a modified algorithm is introduced that is tailored to the specific demands of this study. The proposed approach is validated using a real-world medical dataset and has demonstrated promising results. Two experiments are conducted: the first tasked models with respiratory condition detection when observing mel spectrograms of patients’ breathing patterns, while the second experiment considered the same data format for multiclass classification. Contemporary optimizers are employed to optimize the architecture selection and training parameters of models in both cases. Under identical test conditions, the best models are optimized by the introduced modified metaheuristic, with an accuracy of 0.93 demonstrated for condition detection, and a slightly reduced accuracy of 0.75 for specific condition identification. Full article
(This article belongs to the Special Issue Advances in Parameter-Tuning Techniques for Metaheuristic Algorithms)
Back to TopTop