Detecting Faulty Sensors by Analyzing the Uncertain Data Using Probabilistic Database

Abstract

In today’s era, data is stored for later analysis but most of the significant applications such as WSN, and Medical Science are producing uncertain data. Still, the recorded uncertain data can be analyzed to produce probabilistic answers but the conventional DBMS are designed based on First Order Logic so they are unable to store and process data with some uncertainty or missing values. At the same time, it is not beneficial to delete uncertain data it may affect the result. To deal with uncertain data, Different research groups at the world's renowned institutes developed the Probabilistic DBMS. Like a research group at Oxford University has developed the MayBMS: A probabilistic database management system to analyze the uncertain data. But before using the probabilistic DBMS to manage the uncertain data, the uncertainty in the data should be calculated using probability theory to know the correctness of each record. The purpose of writing this research paper is to find a way to measure the uncertainty available in the data before managing it. Because the management of uncertain data is the second phase, the first thing is to know the correctness or falseness of each available record in the dataset.