Interpretable Diagnostics with SHAP-Rule: Fuzzy Linguistic Explanations from SHAP Values

This study introduces SHAP-Rule, a novel explainable artificial intelligence method that integrates Shapley additive explanations with fuzzy logic to automatically generate interpretable linguistic IF-THEN rules for diagnostic tasks. Unlike purely numeric SHAP vectors, which are difficult for decisi...

Full description

Bibliographic Details

Published in:	Mathematics
Main Authors:	Alexandra I. Khalyasmaa, Pavel V. Matrenin, Stanislav A. Eroshenko
Format:	Article
Language:	English
Published:	MDPI AG 2025-10-01
Subjects:	explainable artificial intelligence Shapley additive explanations fuzzy rules linguistic variables diagnostics
Online Access:	https://www.mdpi.com/2227-7390/13/20/3355