A Fuzzy Logic-based Method for Outliers Detection

S. Cateni, V. Colla, and M. Vannucci (Italy)

Keywords

Fuzzy Logic, Fuzzy Inference System, Outlier Detection, Signal Processing, Intelligent Information Systems

Abstract

The paper presents a method based on a fuzzy inference system that is capable of pointing out outliers in a series of data. The proposed algorithm has been adopted in order to process data coming from a real industrial context. The overall purpose of the work is to point out anomalous data due to several causes such as erroneous measurements, er rors made by the operator that filled the database or anoma lous process conditions. A standard statistical technique for outlier detection as been exploied for the same purpose: the performance obtained by the two methods are compared and discussed.

Important Links:



Go Back