Keywords
machine learning
fuzzy decision trees
fuzzy rule-based systems
hybrid model training
How to Cite
Abstract
The rapid advancements in machine learning (ML) have enabled powerful data-driven models to achieve remarkable performance in diverse application areas. However, most machine learning models operate as "black boxes" and struggle with uncertainty, imprecision, and interpretability challenges. Fuzzy logic, with its capability to model vague concepts and approximate reasoning, offers a promising complementary approach to enhance ML systems. This paper explores the integration of fuzzy logic methods with machine learning, highlighting hybrid approaches such as neuro-fuzzy systems, fuzzy decision trees, and fuzzy clustering. We present a proposed methodology combining fuzzy rule-based systems with supervised ML algorithms to improve model transparency and robustness. Experimental evaluation demonstrates that integrating fuzzy logic enhances interpretability while maintaining competitive accuracy. The study concludes that fuzzy-augmented ML frameworks can provide more human-centric and explainable artificial intelligence solutions.
References
Castillo, O., Melin, P. (2008). Hybrid Intelligent Systems for Pattern Recognition Using Soft Computing. Springer.
Dubois, D., Prade, H. (2015). "The Legacy of Fuzzy Logic." IEEE Computational Intelligence Magazine, 10(4): 22–38.
Gupta, M.M., Jin, L., & Homma, N. (2003). Static and Dynamic Neural Networks: From Fundamentals to Advanced Theory. Wiley.
Jang, J.S.R. (1993). "ANFIS: Adaptive-Network-Based Fuzzy Inference System." IEEE Transactions on Systems, Man, and Cybernetics, 23(3): 665–685
Pedrycz, W. (1998). "Fuzzy Sets in Pattern Recognition: Methodology and Methods." Pattern Recognition, 31(7): 703–719.
Zadeh, L.A. (1965). "Fuzzy Sets." Information and Control, 8(3): 338–353.