1
|
Feda AK, Adegboye M, Adegboye OR, Agyekum EB, Fendzi Mbasso W, Kamel S. S-shaped grey wolf optimizer-based FOX algorithm for feature selection. Heliyon 2024; 10:e24192. [PMID: 38293420 PMCID: PMC10825485 DOI: 10.1016/j.heliyon.2024.e24192] [Citation(s) in RCA: 4] [Impact Index Per Article: 4.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/06/2023] [Revised: 12/09/2023] [Accepted: 01/04/2024] [Indexed: 02/01/2024] Open
Abstract
The FOX algorithm is a recently developed metaheuristic approach inspired by the behavior of foxes in their natural habitat. While the FOX algorithm exhibits commendable performance, its basic version, in complex problem scenarios, may become trapped in local optima, failing to identify the optimal solution due to its weak exploitation capabilities. This research addresses a high-dimensional feature selection problem. In feature selection, the most informative features are retained while discarding irrelevant ones. An enhanced version of the FOX algorithm is proposed, aiming to mitigate its drawbacks in feature selection. The improved approach referred to as S-shaped Grey Wolf Optimizer-based FOX (FOX-GWO), which focuses on augmenting the local search capabilities of the FOX algorithm via the integration of GWO. Additionally, the introduction of an S-shaped transfer function enables the population to explore both binary options throughout the search process. Through a series of experiments on 18 datasets with varying dimensions, FOX-GWO outperforms in 83.33 % of datasets for average accuracy, 61.11 % for reduced feature dimensionality, and 72.22 % for average fitness value across the 18 datasets. Meaning it efficiently explores high-dimensional spaces. These findings highlight its practical value and potential to advance feature selection in complex data analysis, enhancing model prediction accuracy.
Collapse
Affiliation(s)
- Afi Kekeli Feda
- Management Information System Department, European University of Lefke, Mersin, 10, Turkey
| | | | | | - Ephraim Bonah Agyekum
- Department of Nuclear and Renewable Energy, Ural Federal University named after the first President of Russia Boris Yeltsin, 620002, 19 Mira Street, Ekaterinburg, Russia
| | - Wulfran Fendzi Mbasso
- Laboratory of Technology and Applied Sciences, University Institute of Technology, University of Douala, PO Box: 8698, Douala, Cameroon
| | - Salah Kamel
- Department of Electrical Engineering, Faculty of Engineering, Aswan University, Aswan, 81542, Egypt
| |
Collapse
|
2
|
Zhong R, Peng F, Zhang E, Yu J, Munetomo M. Vegetation Evolution with Dynamic Maturity Strategy and Diverse Mutation Strategy for Solving Optimization Problems. Biomimetics (Basel) 2023; 8:454. [PMID: 37887585 PMCID: PMC10604831 DOI: 10.3390/biomimetics8060454] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/19/2023] [Revised: 09/20/2023] [Accepted: 09/20/2023] [Indexed: 10/28/2023] Open
Abstract
We introduce two new search strategies to further improve the performance of vegetation evolution (VEGE) for solving continuous optimization problems. Specifically, the first strategy, named the dynamic maturity strategy, allows individuals with better fitness to have a higher probability of generating more seed individuals. Here, all individuals will first become allocated to generate a fixed number of seeds, and then the remaining number of allocatable seeds will be distributed competitively according to their fitness. Since VEGE performs poorly in getting rid of local optima, we propose the diverse mutation strategy as the second search operator with several different mutation methods to increase the diversity of seed individuals. In other words, each generated seed individual will randomly choose one of the methods to mutate with a lower probability. To evaluate the performances of the two proposed strategies, we run our proposal (VEGE + two strategies), VEGE, and another seven advanced evolutionary algorithms (EAs) on the CEC2013 benchmark functions and seven popular engineering problems. Finally, we analyze the respective contributions of these two strategies to VEGE. The experimental and statistical results confirmed that our proposal can significantly accelerate convergence and improve the convergence accuracy of the conventional VEGE in most optimization problems.
Collapse
Affiliation(s)
- Rui Zhong
- Graduate School of Information Science and Technology, Hokkaido University, Sapporo 060-0808, Japan;
| | - Fei Peng
- Graduate School of Science and Technology, Niigata University, Niigata 950-3198, Japan;
| | - Enzhi Zhang
- Graduate School of Information Science and Technology, Hokkaido University, Sapporo 060-0808, Japan;
| | - Jun Yu
- Institute of Science and Technology, Niigata University, Niigata 950-3198, Japan;
| | - Masaharu Munetomo
- Information Initiative Center, Hokkaido University, Sapporo 060-0808, Japan;
| |
Collapse
|
3
|
Mostafa RR, Gaheen MA, Abd ElAziz M, Al-Betar MA, Ewees AA. An improved gorilla troops optimizer for global optimization problems and feature selection. Knowl Based Syst 2023; 269:110462. [DOI: 10.1016/j.knosys.2023.110462] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 09/02/2023]
|
4
|
Al-Betar MA, Awadallah MA, Makhadmeh SN, Alyasseri ZAA, Al-Naymat G, Mirjalili S. Marine Predators Algorithm: A Review. ARCHIVES OF COMPUTATIONAL METHODS IN ENGINEERING : STATE OF THE ART REVIEWS 2023; 30:3405-3435. [PMID: 37260911 PMCID: PMC10115392 DOI: 10.1007/s11831-023-09912-1] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Figures] [Subscribe] [Scholar Register] [Received: 10/22/2022] [Accepted: 03/05/2023] [Indexed: 06/02/2023]
Abstract
Marine Predators Algorithm (MPA) is a recent nature-inspired optimizer stemmed from widespread foraging mechanisms based on Lévy and Brownian movements in ocean predators. Due to its superb features, such as derivative-free, parameter-less, easy-to-use, flexible, and simplicity, MPA is quickly evolved for a wide range of optimization problems in a short period. Therefore, its impressive characteristics inspire this review to analyze and discuss the primary MPA research studies established. In this review paper, the growth of the MPA is analyzed based on 102 research papers to show its powerful performance. The MPA inspirations and its theoretical concepts are also illustrated, focusing on its convergence behaviour. Thereafter, the MPA versions suggested improving the MPA behaviour on connecting the search space shape of real-world optimization problems are analyzed. A plethora and diverse optimization applications have been addressed, relying on MPA as the main solver, which is also described and organized. In addition, a critical discussion about the convergence behaviour and the main limitation of MPA is given. The review is end-up highlighting the main findings of this survey and suggests some possible MPA-related improvements and extensions that can be carried out in the future.
Collapse
Affiliation(s)
- Mohammed Azmi Al-Betar
- Artificial Intelligence Research Center (AIRC), College of Engineering and Information Technology, Ajman University, Ajman, United Arab Emirates
- Department of Information Technology, Al-Huson University College, Al-Balqa Applied University, Al-Huson, Irbid, Jordan
| | - Mohammed A. Awadallah
- Department of Computer Science, Al-Aqsa University, P.O. Box 4051, Gaza, Palestine
- Artificial Intelligence Research Center (AIRC), Ajman University, Ajman, United Arab Emirates
| | - Sharif Naser Makhadmeh
- Artificial Intelligence Research Center (AIRC), College of Engineering and Information Technology, Ajman University, Ajman, United Arab Emirates
| | - Zaid Abdi Alkareem Alyasseri
- Information Technology Research and Development Center (ITRDC), University of Kufa, An Najaf, 54001 Iraq
- College of Engineering, University of Warith Al-Anbiyaa, Karbalä’, Iraq
| | - Ghazi Al-Naymat
- Artificial Intelligence Research Center (AIRC), College of Engineering and Information Technology, Ajman University, Ajman, United Arab Emirates
| | - Seyedali Mirjalili
- Center for Artificial Intelligence Research and Optimization, Torrens University, Adelaide, Australia
| |
Collapse
|
5
|
Rai R, Dhal KG, Das A, Ray S. An Inclusive Survey on Marine Predators Algorithm: Variants and Applications. ARCHIVES OF COMPUTATIONAL METHODS IN ENGINEERING : STATE OF THE ART REVIEWS 2023; 30:3133-3172. [PMID: 36855410 PMCID: PMC9951854 DOI: 10.1007/s11831-023-09897-x] [Citation(s) in RCA: 1] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Subscribe] [Scholar Register] [Received: 01/02/2023] [Accepted: 02/08/2023] [Indexed: 05/13/2023]
Abstract
Marine Predators Algorithm (MPA) is the existing population-based meta-heuristic algorithms that falls under the category of Nature-Inspired Optimization Algorithm (NIOA) enthused by the foraging actions of the marine predators that principally pursues Levy or Brownian approach as its foraging strategy. Furthermore, it employs the optimal encounter rate stratagem involving both the predator as well as prey. Since its introduction by Faramarzi in the year 2020, MPA has gained enormous popularity and has been employed in numerous application areas ranging from Mathematical and Engineering Optimization problems to Fog Computing to Image Processing to Photovoltaic System to Wind-Solar Generation System for resolving continuous optimization problems. Such huge interest from the research fraternity or the massive recognition of MPA is due to several factors such as its simplicity, ease of application, realistic execution time, superior convergence acceleration rate, soaring effectiveness, its ability to unravel continuous, multi-objective and binary problems when compared with other renowned optimization algorithms existing in the literature. This paper offers a detailed summary of the Marine Predators Algorithm (MPA) and its variants. Furthermore, the applications of MPA in a number of spheres such as Image processing, classification, electrical power system, Photovoltaic models, structural damage detection, distribution networks, engineering applications, Task Scheduling, optimization problems etc., are illustrated. To conclude, the paper highlights and thereby advocates few of the potential future research directions for MPA.
Collapse
Affiliation(s)
- Rebika Rai
- Department of Computer Applications, Sikkim University, Sikkim, India
| | - Krishna Gopal Dhal
- Department of Computer Science and Application, Midnapore College (Autonomous), Paschim Medinipur, West Bengal India
| | - Arunita Das
- Department of Computer Science and Application, Midnapore College (Autonomous), Paschim Medinipur, West Bengal India
| | - Swarnajit Ray
- Department of Computer Science and Engineering, Maulana Abul Kalam Azad University of Technology, Kolkata, West Bengal India
| |
Collapse
|
6
|
Wakili MA, Shehu HA, Sharif MH, Sharif MHU, Umar A, Kusetogullari H, Ince IF, Uyaver S. Classification of Breast Cancer Histopathological Images Using DenseNet and Transfer Learning. COMPUTATIONAL INTELLIGENCE AND NEUROSCIENCE 2022; 2022:8904768. [PMID: 36262621 PMCID: PMC9576400 DOI: 10.1155/2022/8904768] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Received: 05/09/2022] [Revised: 06/19/2022] [Accepted: 07/30/2022] [Indexed: 11/22/2022]
Abstract
Breast cancer is one of the most common invading cancers in women. Analyzing breast cancer is nontrivial and may lead to disagreements among experts. Although deep learning methods achieved an excellent performance in classification tasks including breast cancer histopathological images, the existing state-of-the-art methods are computationally expensive and may overfit due to extracting features from in-distribution images. In this paper, our contribution is mainly twofold. First, we perform a short survey on deep-learning-based models for classifying histopathological images to investigate the most popular and optimized training-testing ratios. Our findings reveal that the most popular training-testing ratio for histopathological image classification is 70%: 30%, whereas the best performance (e.g., accuracy) is achieved by using the training-testing ratio of 80%: 20% on an identical dataset. Second, we propose a method named DenTnet to classify breast cancer histopathological images chiefly. DenTnet utilizes the principle of transfer learning to solve the problem of extracting features from the same distribution using DenseNet as a backbone model. The proposed DenTnet method is shown to be superior in comparison to a number of leading deep learning methods in terms of detection accuracy (up to 99.28% on BreaKHis dataset deeming training-testing ratio of 80%: 20%) with good generalization ability and computational speed. The limitation of existing methods including the requirement of high computation and utilization of the same feature distribution is mitigated by dint of the DenTnet.
Collapse
Affiliation(s)
| | - Harisu Abdullahi Shehu
- School of Engineering and Computer Science, Victoria University of Wellington, Wellington 6012, New Zealand
| | - Md. Haidar Sharif
- College of Computer Science and Engineering, University of Hail, Hail 2440, Saudi Arabia
| | - Md. Haris Uddin Sharif
- School of Computer & Information Sciences, University of the Cumberlands, Williamsburg, KY 40769, USA
| | - Abubakar Umar
- Abubakar Tafawa Balewa University, Bauchi 740272, Nigeria
| | - Huseyin Kusetogullari
- Department of Computer Science, Blekinge Institute of Technology, Karlskrona 37141, Sweden
| | - Ibrahim Furkan Ince
- Department of Digital Game Design, Nisantasi University, 34485 Istanbul, Turkey
| | - Sahin Uyaver
- Department of Energy Science and Technologies, Turkish-German University, 34820 Istanbul, Turkey
| |
Collapse
|