Submission Deadline: 25 August 2021 (closed) View: 143
Metaheuristic techniques are extensively utilized to solve many complex and real-world problems. These techniques do not provide an exact solution, but only an estimated result in feasible time. Recently, many researchers have utilized these techniques for solving the various artificial intelligence (AI) enabled applications. These techniques are generally used in two different ways to improve the AI applications. In first case, these techniques can help for evaluating the potential features from the pool of features of a given machine learning/ deep learning problem. It can improve the performance and computation speed of the given machine learning/ deep learning models. In second approach, metaheuristic techniques are widely accepted to resolve the hyper-parameters tuning issue with the most of machine learning and deep learning models. Even metaheuristic techniques are accepted as a hyper-parameters tuning tool for various kind of other techniques such as chaotic map, deep generative models, fuzzy logic, chaotic maps, etc. Therefore, the metaheuristic techniques have their own importance in various fields of computational sciences. However, most metaheuristic techniques suffer from the pre-mature convergence, stuck in local optima, poor convergence speed, etc. kind of issues.
The purpose of this special issue is to demonstrate the new development and application of metaheuristic techniques. The goal is to promote research and development of metathetic based techniques for real-time applications by publishing high-quality research papers in this interdisciplinary field that can profoundly impact the future of the metaheuristic techniques. Potential topics include, but are not limited to:
• Evolutionary approaches
• Nature inspired optimization techniques
• Swarm intelligence
• Hybrid metaheuristic techniques
• Tuning of hyper-parameters using metaheuristic techniques
• Feature selection using metaheuristic techniques
• Metaheuristic techniques based machine learning models
• Metaheuristic techniques based deep learning models
• Metaheuristic techniques based explainable AI models
• Metaheuristic techniques based real-time applications