Table of Content

Computational Intelligent Systems for Solving Complex Engineering Problems: Principles and Applications

Submission Deadline: 31 December 2022 Submit to Special Issue

Guest Editors

Dr. Danial Jahed Armaghani, University of Technology Sydney, Australia; South Ural State University, Russia
Dr. Ahmed Salih Mohammed, University of Sulaimani, Iraq
Prof. Ramesh Murlidhar Bhatawdekar, Indian Institute of Technology, India; Universiti Teknologi Malaysia, Malaysia
Mr. Pouyan Fakharian, Semnan University, Iran
Dr. Ashutosh Kainthola, Banaras Hindu University, India
Mr. Wael Imad Mahmood, Komar University of Science and Technology, Iraq

Summary

In the last two decades, the topic of computational intelligence (CI) has undergone several definitions. Adaptation and self-organization algorithms and implementations that permit or facilitate appropriate behaviours (intelligent behaviour) in complex and dynamic settings are included in the notion of CI. One or more properties of reason, such as generalisation, discovery, association, and abstraction, are said to be present in this computer paradigm, which demonstrates a capacity to adapt to new conditions and learn from them. Many of the issues we face today in the area of engineering are becoming more complicated because of the prevalence of amorphous structures and behaviours, as well as large-scale, low dependability, and a scarcity of shared or comprehensive information. This intricacy necessitated that the scope of CI is widened to highlight adaptability.

In order to operate a system similar to human thinking, CI relies on three primary components: artificial neural networks, fuzzy logic, and evolutionary computation, both of which employ machine learning theories to cope with uncertainty. Hybrid CI models have shown a greater performance and application level in numerous fields of engineering than conventional CI models, which had serious limitations such time-consuming human participation and a lack of resilience. Metaheuristic algorithms may be utilised to improve base model hyper-parameters (CI models), adding extra value to frequently used base intelligence approaches.

 

This Special Issue focuses on the creation of unique hybrid intelligence strategies for handling regression, classification, and time series challenges. We invite scholars to submit original research papers that will help to promote ongoing research on the use of emerging CI and hybrid CI systems to assess and solve complex engineering challenges. In addition, state-of-the-art research reports, reviews, and critical evaluations of CI and hybrid CI systems are most welcome.


Keywords

Fuzzy and neuro-fuzzy Systems
Support vector machines-based systems
Genetic algorithm and genetic programming
Deep learning-based techniques
Time series systems
Hybrid artificial neural network systems
Evolutionary algorithms
Theory-guided CI systems
Metaheuristic and optimization algorithms

Published Papers


Share Link

WeChat scan