Paper information
Title
Evaluating Heuristics for Tabletop User Segmentation Based on Simultaneous Interaction
Evaluating Heuristics for Tabletop User Segmentation Based on Simultaneous Interaction
Fernando García Sanjuan
Published in
Expert Systems with Applications Volume 40, Issue 14, 15 October 2013, pp. 55785587 - 2013
Expert Systems with Applications Volume 40, Issue 14, 15 October 2013, pp. 55785587 - 2013
Abstract
Differentiating between users that interact on a tabletop could be beneficial for collaborative tasks to support territoriality-oriented features such as a more efficient space management or a better presentation of the contents. In this paper, we design a novel algorithm for the user differentiation or segmentation based on the simultaneous manipulation of controls. This is a potential differentiating factor that has remained unexplored so far, and in combination with other factors may become relevant to successfully accomplish such differentiation task. Basically it relies on the idea that users manipulate digital elements with a single hand, and hence, if two controls are being used at the same time, they most likely belong to different users. On the generic algorithm, three different versions have been implemented that include several heuristics to address the problem. The comparison under a simulated experiment shows that the heuristic involving more knowledge on distances on user controls performed better according to different goodness functions. This shows promising to further development and refinement of the approach by expanding it with other potential factors to eventually build a robust user differentiation subsystem.
Differentiating between users that interact on a tabletop could be beneficial for collaborative tasks to support territoriality-oriented features such as a more efficient space management or a better presentation of the contents. In this paper, we design a novel algorithm for the user differentiation or segmentation based on the simultaneous manipulation of controls. This is a potential differentiating factor that has remained unexplored so far, and in combination with other factors may become relevant to successfully accomplish such differentiation task. Basically it relies on the idea that users manipulate digital elements with a single hand, and hence, if two controls are being used at the same time, they most likely belong to different users. On the generic algorithm, three different versions have been implemented that include several heuristics to address the problem. The comparison under a simulated experiment shows that the heuristic involving more knowledge on distances on user controls performed better according to different goodness functions. This shows promising to further development and refinement of the approach by expanding it with other potential factors to eventually build a robust user differentiation subsystem.
BibTeX
@misc{issi_web:id:427,
title = "Evaluating Heuristics for Tabletop User Segmentation Based on Simultaneous Interaction",
author = "Fernando García Sanjuan and Javier Jaén Martínez and Alejandro Catalá Bolós",
booktitle = "Expert Systems with Applications Volume 40, Issue 14, 15 October 2013, pp. 55785587",
year = "2013",
eprint = "http://issi.dsic.upv.es/publications/archives/",
url = "http://dx.doi.org/10.1016/j.eswa.2013.04.011",
abstract = "Differentiating between users that interact on a tabletop could be beneficial for collaborative tasks to support territoriality-oriented features such as a more efficient space management or a better presentation of the contents. In this paper, we design a novel algorithm for the user differentiation or segmentation based on the simultaneous manipulation of controls. This is a potential differentiating factor that has remained unexplored so far, and in combination with other factors may become relevant to successfully accomplish such differentiation task. Basically it relies on the idea that users manipulate digital elements with a single hand, and hence, if two controls are being used at the same time, they most likely belong to different users. On the generic algorithm, three different versions have been implemented that include several heuristics to address the problem. The comparison under a simulated experiment shows that the heuristic involving more knowledge on distances on user controls performed better according to different goodness functions. This shows promising to further development and refinement of the approach by expanding it with other potential factors to eventually build a robust user differentiation subsystem."
}