Performance measures to enable agent-based support in demanding circumstances

  • Authors:

  • Fiemke Both;Mark Hoogendoorn;Rianne M. van Lambalgen;Rogier Oorburg;Michael de Vos

  • Affiliations:

  • Vrije Universiteit Amsterdam, Department of Artificial Intelligence, Amsterdam, The Netherlands;Vrije Universiteit Amsterdam, Department of Artificial Intelligence, Amsterdam, The Netherlands;Vrije Universiteit Amsterdam, Department of Artificial Intelligence, Amsterdam, The Netherlands;Defence Materiel Organization, CAMS-Force Vision Den Helder, The Netherlands;Defence Materiel Organization, CAMS-Force Vision Den Helder, The Netherlands

  • Venue:
  • FAC'11 Proceedings of the 6th international conference on Foundations of augmented cognition: directing the future of adaptive systems
  • Year:
  • 2011

Quantified Score

Hi-index 0.00

Visualization

Abstract

In this paper, an evaluation of measurements that can be used by a personal support agent to measure the quality of human task performance is addressed. Such measurements are important in order for a support agent to give effective and personalized support during the performance of demanding tasks. Hereby, the performance quality measurement is addressed from two perspectives, namely the human's perspective as well as the task perspective. The former represents the idea the human has about the current task performance, whereas the latter measures the actual task performance compared to the goals set for the task at hand. Criteria have been identified to compare the various measurements, and an experiment has been conducted for evaluation. Based on these evaluation results, the most useful measurements are identified to be adopted within personal support agents.