Strong Robust Similarity Measures: A Detailed Analysis and Application

Similarity measures are fundamental tools for comparing and evaluating data across various domains. Robust similarity measures extend classical similarities. However, when dealing with interval data, robust measures are often insufficient due to the intrinsic properties of intervals. In this study, we introduce the concept of strong robust similarity measures, which incorporate three additional axioms specifically considered to manage uncertainty represented by intervals. Furthermore, we characterize these measures through a novel class of functions, referred to as preinclusions. We also provide a comprehensive analysis of the proposed measures, examining their behaviour with respect to different axioms. Finally, we illustrate the applicability of our approach through a real-world case study using meteorological data collected by AEMET (the Spanish National Weather Service) in ۲۰۲۱.

کلیدواژه ها:

Similarity measure ، robust similarity ، strong robust similarity ، interval ، overlapping degree ، meteorological data