Neuro-Fuzzy Systems in the Age of AI: Challenges, Innovations, and Future Directions

In the evolving landscape of artificial intelligence, neuro-fuzzy systems represent a promising hybrid approach that combines the learning capabilities of neural networks with the interpretability of fuzzy logic.This study proposes a Fuzzy Inference System (FIS) model developed in MATLAB 2023a to assess the advancement level of neuro-fuzzy systems in the age of AI.The model utilizes three key input variables-Complexity of AI Integration, Level of Innovation, and Future Scalability Potential-to evaluate their impact on the overall performance and maturity of such systems.Each input and output is defined using triangular membership functions to reflect linguistic variables such as "Low", "Medium", and "High".A rule base of nine expert-defined fuzzy rules guides the decision-making process.Simulation results demonstrate that the FIS model can effectively evaluate neuro-fuzzy architectures, providing insights into their strengths and areas for future enhancement.This approach offers a flexible and explainable framework for benchmarking hybrid intelligent systems and supports strategic decision-making in AI-driven system design and development.