The Usage of Probability Theory Concepts for Analysing Big Data Uncertainty Reasoning

Partial observability, nondeterminism or a combination of the two develop the problem of uncertainty a common occurrence in big data. An agent is needed to handle this uncertainty. This paper aims to see how an agent can tame uncertainty with the degree of belief and to design an agent program that implements the agent function, the mapping from percepts to actions, especially in the field of big data where volumes of data needs to be handled. The agent program more often takes the current percept as input from the sensors and return an action. Uncertainty arises because of ignorance or volumes of data; The agent’s lack to express the truth of the event in the sentence due to uncertainty that prevails, which can be expressed using probability. Probabilities summarises the agent’s belief relative to the evidence and probability distribution is used to specify the probability that exist in assigning to any random variables. Partial observability of the world brings in unobserved aspects, these can be resolved by estimating the values using probability, that help better agent decision in any field including big data. The agent program come into being through learning methods. An agent is designed to form representations of a complex world, the world with huge voluminous data, use a process of inference to derive new representations about the world, and use these new representations to deduce what to do.