An integrated agent model for attention and functional state

  • Authors:

  • Tibor Bosse;Rianne van Lambalgen;Peter-Paul van Maanen;Jan Treur

  • Affiliations:

  • Department of Artificial Intelligence, Vrije Universiteit Amsterdam, Amsterdam, The Netherlands;Department of Artificial Intelligence, Vrije Universiteit Amsterdam, Amsterdam, The Netherlands;Department of Artificial Intelligence, Vrije Universiteit Amsterdam, Amsterdam, The Netherlands,TNO Human Factors, Soesterberg, The Netherlands;Department of Artificial Intelligence, Vrije Universiteit Amsterdam, Amsterdam, The Netherlands

  • Venue:
  • IEA/AIE'12 Proceedings of the 25th international conference on Industrial Engineering and Other Applications of Applied Intelligent Systems: advanced research in applied artificial intelligence
  • Year:
  • 2012

Quantified Score

Hi-index 0.00

Visualization

Abstract

To provide personalized intelligent ambient support for persons performing demanding tasks, it is important to have insight in their state of attention. Existing models for attention have difficulties in distinguishing between stressed and relaxed states. To solve this problem, this paper proposes to extend an existing model for attention with a model for ‘functional state'. In this integrated agent model, output of a functional state model (experienced pressure) serves as input for the attention model; the overall amount of attention is dependent on the amount of experienced pressure. An experiment was conducted to test the validity of the integrated agent model against the validity of an earlier model based on attention only. Results pointed out that the integrated model had a higher validity than the earlier model and was more successful in predicting attention.