Outlier Elimination: Granular Box Regression using Z-Score

Granular computing has gained increasing attention in the last decade. Although not uniquely defined, its basic idea is to approximate detailed machine-like information by a coarser presentation on a human-like level. It is motivated by the needs for simply and robust low cost solutions in real life applications. Within this framework, granular box regression was proposed recently and uses hyper-dimensional interval numbers to establish a function between independent variables and dependent variable. A regression method desires to fit the curve on a data set irrespective of outliers. This paper modifies the granular box regression approaches to deal with outliers by using z-score method. The performance of the proposed approach are investigated in terms of volume of boxes, insensitivity to outliers, elapsed time for box configuration and error of regression. The proposed approach offers a better linear model on the given artificial datasets containing varieties of outlier rates.

Keywords:

Granular Box Regression , Outlier Elimination , Z-Score , Granular Computing.