Using entropy for dimension reduction of tactile data

Author

Sch?¶pfer, Matthias ; Pardowitz, Michael ; Ritter, Helge

Author_Institution

Fac. of Technol., Bielefeld Univ., Bielefeld, Germany

fYear

2009

Firstpage

1

Lastpage

6

Abstract

Tactile sensing arrays for robotic applications become more and more popular these days. This allows us to equip robots with sensing abilities similar to those of our human skin. This paper presents an approach to tactile-based recognition of objects and evaluates the utility of various feature extractors for tactile processing. Extracting these features from a tactile database, we describe a system that combines a discretization step with the well-known C4.5 algorithm in an object classification task. We analyse the usefulness of the features in terms of entropy-based considerations taking into account the generated decision trees and report our results that give important hints for feature selection.

Keywords

decision trees; entropy; feature extraction; intelligent robots; learning (artificial intelligence); object recognition; pattern classification; tactile sensors; C4.5 machine learning algorithm; decision tree; discretization step; entropy-based consideration; feature extraction; feature selection; human skin; object classification; robotic application; tactile data dimensionality reduction; tactile database; tactile object processing; tactile sensing array; tactile-based object recognition; Decision trees; Entropy; Feature extraction; Humans; Robot sensing systems; Sensor arrays; Signal processing algorithms; Skin; Spatial databases; Tactile sensors;

fLanguage

English

Publisher

ieee

Conference_Titel

Advanced Robotics, 2009. ICAR 2009. International Conference on

Print_ISBN

978-1-4244-4855-5

Electronic_ISBN

978-3-8396-0035-1

Type

conf

Filename

5174811