Weighted Similarity and Distance Measures for T‐Spherical Fuzzy Sets and Their Applications in Deep Learning Classifications

ABSTRACT T‐spherical fuzzy sets (TSFSs) provide a robust and flexible framework for modeling uncertainty by aggregating membership, nonmembership, and neutrality degrees using t‐norms. This study introduces a new family of set‐theoretic weighted similarity and distance measures specifically designed for TSFSs, which should pique curiosity about their innovative approach. This study demonstrates that numerous traditional measurements fail to satisfy fundamental axiomatic properties. Conversely, our suggested measurements demonstrate unwavering reliability and efficacy over a wide range of scenarios. To validate the practical utility of these measures, we integrate them into a deep learning classification framework. Finally, we apply the proposed similarity measurement to deep learning classification of 3D CT scans. It can improve classification accuracy by effectively handling uncertain features in medical imaging data.