LightBlog
Contact at mumbai.academics@gmail.com or 8097636691/9323040215
Responsive Ads Here

Friday, 8 June 2018

Focusing on a Probability Element: Parameter Selection of Message Importance Measure in Big Data

Abstract:-


Message importance measure (MIM) is applicable to characterize the importance of information in the scenario of big data, similar to entropy in information theory. In fact, MIM with a variable parameter can make an effect on the characterization of distribution. Furthermore, by choosing an appropriate parameter of MIM, it is possible to emphasize the message importance of a certain probability element in a distribution. Therefore, parametric MIM can play a vital role in anomaly detection of big data by focusing on probability of an anomalous event. In this paper, we propose a parameter selection method of MIM focusing on a probability element  and then present its major properties. In addition, we discuss the parameter selection with prior probability, and investigate the availability in a statistical processing model of big data for anomaly detection problem

No comments:

Post a Comment