Design and Evaluation of Adaptative Multimodal Systems

• Main Author: Duarte, Carlos
• Publication Date: 2008
• Language: por
• Source: Repositórios Científicos de Acesso Aberto de Portugal (RCAAP)
• Download full: http://hdl.handle.net/10451/14293
• topic: Adaptive Multimodal Interfaces; Evaluation; Design; FAME; Behavioral Matrix

This thesis focuses on the design and evaluation of adaptive multimodal systems. The design of such systems is approached from an integrated perspective, with the goal of obtaining a solution where aspects related to both adaptive and multimodal systems are considered. The result is FAME, a model based framework for the design and development of adaptive multimodal systems, where adaptive capabilities impact directly over the process of multimodal fusion and fission operations. FAME overviews the design of systems capable of adapting to a diversified context, including variations in users, execution platform, and environment. FAME represents an evolution from previous frameworks by incorporating aspects specific to multimodal interfaces directly in the development of an adaptive platform. One of FAME's components is the Behavioral Matrix, a multipurpose instrument, used during the design phase to represent the adaptation rules. In addition, the Behavioral Matrix is also the component responsible for bridging the gap between design and evaluation stages. Departing from an analogy between transition networks for representing interaction with a system, and behavioral spaces, the Behavioral Matrix makes possible the application of behavioral complexity metrics to general adaptive systems. Moreover, this evaluation is possible during the design stages, which translates into a reduction of the resources required for evaluation of adaptive systems. The Behavioral Matrix allows a designer to emulate the behavior of a non-adaptive version of the adaptive system, allowing for comparison of the versions, one of the most used approaches to adaptive systems evaluation. In addition, the designer may also emulate the behavior of different user profiles and compare their complexity measures. The feasibility of FAME was demonstrated with the development of an adaptive multimodal Digital Book Player. The process was successful, as demonstrated by usability evaluations. Besides these evaluations, behavioral complexity metrics, computed in accordance with the proposed methodology, were able to discern between adaptive and non-adaptive versions of the player. When applied to user profiles of different perceived complexity, the metrics were also able to detect the different interaction complexity