q-Spherical Fuzzy Rough Frank Aggregation Operators in AI Neural Networks: Applications in Military Transport Systems

Abstract

This study introduces a novel neural network approach integrating q-spherical fuzzy rough Frank aggregation operators, aiming to enhance AI systems’ resilience to uncertain and imprecise data in military transport systems. Three new operators are developed: q-spherical fuzzy rough Frank weighted averaging (q-SFRFWA), q-spherical fuzzy rough Frank ordered weighted averaging (q-SFRFOWA), and q-spherical fuzzy rough Frank hybrid weighted averaging (q-SFRFHWA), tailored to handle complex decision-making scenarios. We demonstrate their efficacy in multiple attribute decision-making using q-spherical fuzzy rough data, providing valuable insights and expanding the knowledge base in this domain. Through numerical examples, we illustrate the practical application of these operators, validating their effectiveness and relevance in real-world settings. Comparative and sensitivity analyses further corroborate the superiority of our proposed approach over existing methods. This research offers a robust decision-making framework equipped to manage intricate and unreliable data, promising significant advancements in military transport systems and beyond.

Keywords

• q-spherical fuzzy rough sets
• Frank operators
• neural network in artificial intelligence