Competitive swarm optimizer with dynamic multi-competitions and convergence accelerator for large-scale optimization problems

Applied Soft Computing, Journal Year: 2024, Volume and Issue: unknown, P. 112252 - 112252

Published: Sept. 1, 2024

Language: Английский

---

Feature selection algorithm based on optimized genetic algorithm and the application in high-dimensional data processing

PLoS ONE, Journal Year: 2024, Volume and Issue: 19(5), P. e0303088 - e0303088

Published: May 9, 2024

High-dimensional data is widely used in many fields, but selecting key features from it challenging. Feature selection can reduce dimensionality and weaken noise interference, thereby improving model efficiency enhancing interpretability. In order to improve the accuracy of high-dimensional processing, a feature method based on optimized genetic algorithm proposed this study. The simulates process natural selection, searches for possible subsets feature, finds that optimizes performance model. results show when value K less than 4 or more 8, recognition rate very low. After adaptive bias filtering, 724 are filtered 372, improved 0.9352 0.9815. From 714 406 Gaussian codes, 0.9625 0.9754. Among all tests, colon has highest average accuracy, followed by small round blue cell tumor(SRBCT), lymphoma, central nervous system(CNS) ovaries. green curve best, with stable time range 0–300. While maintaining efficiency, reach 4.48 as soon possible. practical significance improves provides an effective new processing.

Language: Английский

---

Chaotic-Based Mountain Gazelle Optimizer for Solving Optimization Problems

International Journal of Computational Intelligence Systems, Journal Year: 2024, Volume and Issue: 17(1)

Published: May 6, 2024

Abstract The Mountain Gazelle Optimizer (MGO) algorithm has become one of the most prominent swarm-inspired meta-heuristic algorithms because its outstanding rapid convergence and excellent accuracy. However, MGO still faces premature convergence, making it challenging to leave local optima if early-best solutions neglect relevant search domain. Therefore, in this study, a newly developed Chaotic-based (CMGO) is proposed with numerous chaotic maps overcome above-mentioned flaws. Moreover, ten distinct were simultaneously incorporated into determine optimal values enhance exploitation promising solutions. performance CMGO been evaluated using CEC2005 CEC2019 benchmark functions, along four engineering problems. Statistical tests like t-test Wilcoxon rank-sum test provide further evidence that outperforms existing eminent algorithms. Hence, experimental outcomes demonstrate produces successful auspicious results.

Language: Английский

---

Visualization and classification of mushroom species with multi-feature fusion of metaheuristics-based convolutional neural network model

Applied Soft Computing, Journal Year: 2024, Volume and Issue: 164, P. 111936 - 111936

Published: July 4, 2024

Language: Английский

---

Recent applications and advances of African Vultures Optimization Algorithm

Artificial Intelligence Review, Journal Year: 2024, Volume and Issue: 57(12)

Published: Oct. 17, 2024

Language: Английский

---

Multi-objective optimization algorithms for intrusion detection in IoT networks: A systematic review

Internet of Things and Cyber-Physical Systems, Journal Year: 2024, Volume and Issue: 4, P. 258 - 267

Published: Jan. 1, 2024

The significance of intrusion detection systems in networks has grown because the digital revolution and increased operations. method classifies network traffic as threat or normal based on data features. Intrusion system faces a trade-off between various parameters such accuracy, relevance, redundancy, false alarm rate, other objectives. paper presents systematic review Internet Things (IoT) using multi-objective optimization algorithms (MOA), to identify attempts at exploiting security vulnerabilities reducing chances attacks. MOAs provide set optimized solutions for process highly complex IoT networks. This identification multiple objectives detection, comparative analysis their approaches, datasets used evaluation. show encouraging potential enhance conflicting detection. Additionally, current challenges future research ideas are identified. In addition demonstrating new advancements techniques, this study gaps that can be addressed while designing

Language: Английский

---

A review of nature-inspired algorithms on single-objective optimization problems from 2019 to 2023

Artificial Intelligence Review, Journal Year: 2024, Volume and Issue: 57(5)

Published: April 24, 2024

Abstract The field of nature inspired algorithm (NIA) is a vital area research that consistently aids in solving optimization problems. One the metaheuristic classifications has drawn attention from researchers recent decades NIA. It makes significant contribution by addressing numerous large-scale problems and achieving best results. This aims to identify optimal NIA for single-objective discovered between 2019 2023 presented this study with brief description. About 83 distinct NIAs have been studied order address issues. In accomplish goal, we taken into consideration eight real-world problems: 3-bar truss design problem, rolling element bearing, pressure vessel, cantilever beam, I welded spring. Based on comparative bibliographic analysis, determined two algorithms—the flow direction algorithm, prairie dog optimization—give us results solutions all engineering listed. Lastly, some perspectives limitations, difficulties, future course are provided. addition providing guidelines, will assist novice emerging researcher more comprehensive perspective advanced

Language: Английский

---

MaOSSA: A New High-Efficiency Many-Objective Salp Swarm Algorithm with Information Feedback Mechanism for Industrial Engineering Problems

Results in Engineering, Journal Year: 2025, Volume and Issue: unknown, P. 104372 - 104372

Published: Feb. 1, 2025

Language: Английский

---

A novel marine predator whale optimization algorithm for global numerical optimization

Engineering Optimization, Journal Year: 2025, Volume and Issue: unknown, P. 1 - 37

Published: March 31, 2025

---

A Hybrid Model Based on Convolutional Neural Network and Long Short-Term Memory for Multi-label Text Classification

Neural Processing Letters, Journal Year: 2024, Volume and Issue: 56(2)

Published: Feb. 16, 2024

Abstract Multi-label text classification (MLTC) is a popular method for organizing electronic documents, which crucial accessing and processing data. As the number of classes increases, learning multi-label data will be challenging. The possible states various labels increases exponentially, algorithms in single-label cannot used to solve these problems. In meantime, using could very time-consuming. MLTC, complexity costs should reduced. Deep-learning neural networks that can learn intricate patterns are many real-world problems because their high power accuracy. This paper proposed hybridization long short-term memory (LSTM) network convolutional (CNN) MLTC. model uses LSTM enhance CNN improve model’s Also, competitive search algorithm (CSA) hyperparameters. hyperparameters play an important role increasing detection CSA finds best values by searching problem space. It was tested on four different datasets texts: Reuters-21578, RCV1-v2, EUR-Lex, Bookmarks. result showed performed better than LSTM-CSA terms accuracy percentage it has improved average more 10%. results show higher compared LSTM—Gradient-based optimizer (GBO) LSTM—whale optimization (WOA).

Language: Английский

---