Enhancement of Approximation Spaces by the Use of Primals and Neighborhood

TL;DR

This paper introduces four new generalized rough set models based on neighborhoods and primals, aiming to reduce uncertainty regions and improve data analysis accuracy, especially in health-related applications.

Contribution

The paper proposes four novel rough set models that enhance approximation operators and accuracy by leveraging neighborhoods and primals, extending existing models' capabilities.

Findings

Models outperform existing methods in approximation accuracy

Preserve key properties like monotonicity for better data uncertainty assessment

Application to health data yields more precise results

Abstract

Rough set theory is one of the most widely used and significant approaches for handling incomplete information. It divides the universe in the beginning and uses equivalency relations to produce blocks. Numerous generalized rough set models have been put out and investigated in an effort to increase flexibility and extend the range of possible uses. We introduce four new generalized rough set models that draw inspiration from "neighborhoods and primals" in order to make a contribution to this topic. By minimizing the uncertainty regions, these models are intended to assist decision makers in more effectively analyzing and evaluating the provided data. We verify this goal by demonstrating that the existing models outperform certain current method approaches in terms of improving the approximation operators (upper and lower) and accuracy measurements. We claim that the current models can preserve nearly all significant aspects associated with the rough set model. Preserving the monotonic property, which enables us to assess data uncertainty and boost confidence in outcomes, is one of the intriguing characterizations derived from the existing models. With the aid of specific instances, we also compare the areas of the current approach. Finally, we demonstrate that the new strategy we define for our everyday health-related problem yields more accurate findings.