Evolutionary Based Adaptive User Interfaces in Complex Supervisory Tasks

Evolutionary Based Adaptive User Interfaces in Complex Supervisory Tasks

Gary G. Yen (Oklahoma State University, USA)
DOI: 10.4018/978-1-60566-798-0.ch007


In this chapter, the author proposes a novel idea based on evolutionary algorithm for adaptation of the user interface in complex supervisory tasks. Under the assumption that the user behavior is stationary and that the user has limited cognitive and motor abilities, the author has shown that a combination of genetic algorithm for constrained optimization and probabilistic modeling of the user may evolve the adaptive interface to the level of personalization. The non-parametric statistics has been employed to evaluate the feasibility of the ranking approach. The method proposed is flexible and easy to use in various problem domains. The author has tested the method with an automated user and a group of real users in an air traffic control environment. The automated user, implemented for initial tests, is built under the same assumptions as a real user. In the second step, the author has exploited the adaptive interface through a group of real users and collected subjective ratings using questionnaires. The author has shown that the proposed method can effectively improve human-computer interaction and his approach is pragmatically a valid design for the interface adaptation in complex environments.
Chapter Preview

Literature Review On Conceptual Framework For Adaptation

In the introduction, we have mentioned that adaptation of the interface is deemed to be the remedy for human errors in complex environments. The interface adaptation, on the other hand, is not a straightforward task. Difficulty lies in first assessing the user’s state of mind (goal-subgoal structure), state of psychology (situation awareness), and level of vigilance. All of these are non-deterministic and hard to model. Secondly, defining an appropriate adaptation behavior for the interface; and thirdly timeliness of the adaptation (Horvitz, 1999) are the other difficulties. Since the work undertaken in this area of research is not well defined, and hard to attack without an appropriate tool, we need to define a framework before we can start the discussion. There are three steps to be considered in adaptation of the interface. Many papers have been written on adaptation and adaptation methods, however Rothrock et al. (2002) have defined a simple and comprehensive framework for adaptation. In this study we will follow Rothrock’s methodology: identification of variables that call for adaptation, determination of necessary modifications to the interface and selection of decision inference mechanism.

Complete Chapter List

Search this Book: