Abstract: “Most real databases contain data whose correctness is uncertain. In order to work with such data, there is a need to quantify the integrity of the data. This is achieved by using probabilistic databases. Data uncertain is common in real world applications. The uncertainty can be controlled very prudently. In this paper, we are using probabilistic models on uncertain data and develop a novel method to calculate conditional probabilities for uncertain numerical attributes. Based on that, we propose a Naive Bayesian classifier algorithm for uncertain data(NBCU) using exponential distribution. The ultimate aim is determine the uncertainty of multiple attributes using our proposed approach (NBCU).The experimental results show that the proposed method classifies uncertain data with potentially higher accuracy.”

Keywords: Uncertainity, Exponential Distribution, Naïve Bayesian classifier, conditional probability