Coupling of Rough Set Theory and Predictive Power of SVM Towards Mining of Missing Data

Abstract

Rough set theory offers a novel approach to identifying structural correlations amidst imprecise or noisy data, particularly applicable to variables with diverse values. It presents a promising avenue for handling fuzzy, conflicting, and uncertain data, with recent models incorporating various fuzzy generalizations. This technique stands out as a popular solution within artificial intelligence, particularly in data analysis and processing tasks. In the medical domain, where missing data poses a significant challenge, leveraging rough set theory alongside machine learning algorithms for disease prediction is common. This paper proposes a model that effectively predicts missing values using rough set theory, addressing the prevalent issue of incomplete data. By providing a systematic approach and robust algorithm, the model demonstrates the adaptability and potential of rough set theory in contemporary data analysis scenarios. Classification of the predicted data set using supervised Learning Model (SVM) results in accuracy of 82.1% while the F1 score is 82.6%. Through validation with reallife medical datasets using supervised classification techniques, the paper underscores the accuracy and applicability of the proposed algorithm, offering a valuable tool for researchers and practitioners grappling with the complexities of modern data analysis.