Advances in Fuzzy Logic and Artificial Neural Networks

1. Introduction

Fuzzy logic and artificial neural networks are among the most prominent AI approaches, recognized for their importance across various domains. Since its introduction by Professor Lotfi Zadeh in 1965, fuzzy logic has been the subject of numerous theoretical studies and practical applications. Over the years, several extensions of fuzzy logic have been developed to better model different uncertainty phenomena. Consequently, fuzzy logic has proven to be a robust framework for handling subjective, imprecise, ambiguous, or incomplete information. It finds frequent use in control systems, decision-making processes, expert systems, and recommendation engines. Despite the extensive body of research, fuzzy logic remains a fertile and relevant study area that attracts significant academic interest.

Similarly, artificial neural networks have evolved remarkably since their inception in the mid-20th century. Advances in network architectures, training algorithms, development tools, and computational power have significantly expanded their application. Artificial neural networks excel due to their learning capabilities, memory, fault tolerance, and distributed processing. These advantages explain their widespread use in tasks such as value prediction, pattern recognition, clustering, anomaly detection, natural language processing, and image generation.

Given these AI techniques’ vast applicability and importance, I am honored to introduce this Special Issue in Mathematics on “Advances in Fuzzy Logic and Artificial Neural Networks.” This Special Issue features 10 papers selected through a rigorous blind review process. In total, 34 authors from 16 countries contributed to these publications. The distribution of countries of the authors is illustrated in Figure 1, derived from

Table 1. Countries of the authors of the articles published in this Special Issue.

Country	Count
Greece	6
Brazil	5
Spain	3
The Republic of Korea	3
The Czech Republic	3
Serbia	2
Pakistan	2
Saudi Arabia	2
Portugal	1
Russia	1
Norway	1
Bulgaria	1
Israel	1
Chile	1
Germany	1
The United Kingdom	1
Total	34

. Notably, the majority of contributors are from Greece and Brazil.

2. Brief Overview of the Contributions to the Special Issue

This Special Issue combines groundbreaking research that explores AI approaches across diverse contexts, showcasing interdisciplinary solutions to complex challenges.

In “Integrating Fuzzy C-Means Clustering and Explainable AI for Robust Galaxy Classification”, the authors combine fuzzy C-means clustering with explainable AI methods, such as SHAP and LIME, to enhance the accuracy of galaxy classification while addressing data uncertainty from the Galaxy Zoo project. This method not only improves classification performance but also suggests potential applications for environmental management. Similarly, in “Simulations and Bisimulations between Weighted Finite Automata Based on Time-Varying Models over Real Numbers”, the use of dynamic neural systems to solve simulation and bisimulation problems in weighted finite automata, coupled with advanced mathematical techniques, highlights the evolving role of AI in tackling complex problems.

The application of fuzzy logic extends to financial forecasting in “A Fuzzy Multi-Criteria Evaluation System for Share Price Prediction”, where fuzzy systems outperform neural networks in predicting Tesla stock trends. The article “Analysis of the Level of Adoption of Business Continuity Practices by Brazilian Industries” applies Fuzzy TOPSIS to assess business continuity practices, providing insights into the resilience of companies across various sectors. In addition, “An Overview of Applications of Hesitant Fuzzy Linguistic Term Sets in Supply Chain Management” offers a comprehensive review of HFLTS techniques, identifying emerging trends and opportunities in supply chain optimization.

This Special Issue also includes innovative applications of neural networks, such as “Neural Network-Based Design of a Buck Zero-Voltage-Switching Quasi-Resonant DC–DC Converter”, which focuses on energy-efficient converter design. In “M-Polar Fuzzy Graphs and Deep Learning for the Design of Analog Amplifiers”, a hybrid methodology combining deep learning and fuzzy graphs is presented to optimize analog amplifier design.

Healthcare applications are also a key focus. “Applying Neural Networks on Biometric Datasets for Screening Speech and Language Deficiencies in Child Communication” utilizes neural networks to identify speech deficiencies in children, aiding in early clinical diagnoses. “A New Method for Commercial-Scale Water Purification Selection Using Linguistic Neural Networks” proposes a hierarchical linguistic neural network for selecting the most effective water purification methods. Lastly, “FADS: An Intelligent Fatigue and Age Detection System” introduces an AI-powered system to monitor fatigue and age, with potential applications in healthcare monitoring.

This compilation underscores the transformative potential of fuzzy logic and neural networks, driving advances across diverse domains such as science, industry, and healthcare. These studies highlight AI’s versatility and open new avenues for research and practical application in addressing some of today’s most pressing challenges.