Copyright © 2026 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{187547,
        author = {Chitranshu Saxena and Sushil Kumar Dhaneliya},
        title = {Performance Evaluation of Neural Network for Solving Fuzzy Differential Equations Using Root Concatenation},
        journal = {International Journal of Innovative Research in Technology},
        year = {2025},
        volume = {12},
        number = {6},
        pages = {5872-5883},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=187547},
        abstract = {Fuzzy Differential Equations, which incorporate uncertainty through fuzzy logic, are widely used in modeling real-world systems with imprecise data but are challenging to solve using traditional analytical methods. This study introduces a neural network-based solution framework that combines root concatenation with deep learning models to improve accuracy and robustness. The proposed method utilizes root extraction techniques such as Bisection method to generate structured datasets comprising exact, actual, and predicted roots. Convolutional Neural Networks & Long Short-Term Memory architectures are trained using these types of datasets. Contrasted with LSTM's 99.3% accuracy, 98.9% precision, 99.0% recall, and 98.7% F1-score, CNN's experimental findings show that it attains 98.3% accuracy, 97.9% precision, and 98.7% recall. Furthermore, regression metrics such as RMSE (0.0038), MAE (0.0027), and MSE (0.000015) confirm LSTM’s superior predictive performance. This approach provides a reliable, data-driven solution for efficiently solving complex fuzzy systems.},
        keywords = {},
        month = {November},
        }