A new Hyper-heuristic based on Adaptive Simulated Annealing and Reinforcement Learning for the Capacitated Electric Vehicle Routing Problem

Expert Systems with Applications, Journal Year: 2024, Volume and Issue: 252, P. 124197 - 124197

Published: May 20, 2024

Language: Английский

---

Multi-threshold image segmentation using an enhanced fruit fly optimization for COVID-19 X-ray images

Biomedical Signal Processing and Control, Journal Year: 2023, Volume and Issue: 86, P. 105147 - 105147

Published: June 16, 2023

Language: Английский

---

Salp swarm algorithm with iterative mapping and local escaping for multi-level threshold image segmentation: a skin cancer dermoscopic case study

Journal of Computational Design and Engineering, Journal Year: 2023, Volume and Issue: 10(2), P. 655 - 693

Published: Jan. 11, 2023

Abstract If found and treated early, fast-growing skin cancers can dramatically prolong patients’ lives. Dermoscopy is a convenient reliable tool during the fore-period detection stage of cancer, so efficient processing digital images dermoscopy particularly critical to improving level cancer diagnosis. Notably, image segmentation part preprocessing essential technical support in process processing. In addition, multi-threshold (MIS) technology extensively used due its straightforward effective features. Many academics have coupled different meta-heuristic algorithms with MIS raise quality. Nonetheless, these frequently enter local optima. Therefore, this paper suggests an improved salp swarm algorithm (ILSSA) method that combines iterative mapping escaping operator address drawback. Besides, also proposes ILSSA-based approach, which triumphantly utilized segment dermoscopic cancer. This uses two-dimensional (2D) Kapur’s entropy as objective function employs non-local means 2D histogram represent information. Furthermore, array benchmark test experiments demonstrated ILSSA could alleviate optimal problem more effectively than other compared algorithms. Afterward, experiment displayed proposed obtained superior results peers was adaptable at thresholds.

Language: Английский

---

Semantic segmentation using Firefly Algorithm-based evolving ensemble deep neural networks

Knowledge-Based Systems, Journal Year: 2023, Volume and Issue: 277, P. 110828 - 110828

Published: July 25, 2023

Automatic segmentation of salient objects in real-world images has gained increasing interests owing to its popularity diverse applications, such as autonomous driving, medical diagnosis, aviation security, and underwater surveillance. In this research, we propose Firefly Algorithm (FA)-enhanced evolving ensemble deep networks for semantic visual saliency prediction. An improved FA model is proposed optimize network hyper-parameters. Specifically, it employs mutation operators a neighbouring search strategy with granular steps establish intensification. It also emphasizes diversification by adopting multiple dynamic hybrid leaders adaptive sine cosine trajectories full randomly selected sub-dimensions overcome stagnation. Because competent performance, DeepLabV3+ fine-tuned using transfer learning FA-based hyper-parameter identification. We the rate, momentum weight decay network. A number optimized distinguishing configurations are yielded. subsequently constructed incorporating three base further strengthen performance. Evaluated challenging prediction tasks image data sets, our illustrates significant superiority over other state-of-the-art existing studies. The outperforms methods solving mathematical landscapes statistical significance.

Language: Английский

---

SYNTROPY: TCP SYN DDoS attack detection for Software Defined Network based on Rényi entropy

Computer Networks, Journal Year: 2024, Volume and Issue: 244, P. 110327 - 110327

Published: March 12, 2024

Language: Английский

---

Pareto-Based Multiobjective Optimisation for JPEG Image Compression

Studies in computational intelligence, Journal Year: 2025, Volume and Issue: unknown, P. 135 - 157

Published: Jan. 1, 2025

Language: Английский

---

Enhancing Neural Network Generalisation with Improved Differential Evolution

Studies in computational intelligence, Journal Year: 2025, Volume and Issue: unknown, P. 455 - 470

Published: Jan. 1, 2025

Language: Английский

---

Performance optimization of hunger games search for multi-threshold COVID-19 image segmentation

Multimedia Tools and Applications, Journal Year: 2023, Volume and Issue: 83(8), P. 24005 - 24044

Published: Aug. 7, 2023

Language: Английский

---

A binary tree seed algorithm with selection-based local search mechanism for huge-sized optimization problems

Applied Soft Computing, Journal Year: 2022, Volume and Issue: 129, P. 109590 - 109590

Published: Sept. 5, 2022

Language: Английский

---

Metaheuristic-based energy-aware image compression for mobile app development

Multimedia Tools and Applications, Journal Year: 2024, Volume and Issue: unknown

Published: May 2, 2024

Language: Английский

---