From probabilistic computing approach to probabilistic rough set for solving problem related to uncertainty under machine learning

Abstract

Box and Tiao suggested about the prior distribution, which according to them is hypothetically representing the knowledge about anonymous constraints prior to the availability of data. It acts as a productive role in Bayesian analysis. Further, allotments of such kind also represent former knowledge or relative ignorance [4]. The chance of occurrence or predictability is defined by the term Probability. During the availability of partial information related to the result, the calculation becomes more challenging. Even the partial results are also not available in some real world scenario. Several literatures are available in this direction. Pawlak's Rough sets, decision algorithms and Bayes Theorem is in the used to analyze the result in same direction. In our paper, we have extended our work where we have thoroughly studied and tried to create a relationship from probabilistic computing and Rough sets. We have further extended our study the importance of decision making by the concept of probabilistic rough set. Generally, the paper presents a kind of survey, where we intend to model a decision based system which can work efficiently under uncertainty.