Making systems sensitive to the user's changing resource limitations

Jameson, Anthony; Schäfer, Reiner; Weis, T.; Berthold, André; Weyrath, Thomas

doi:10.1016/s0950-7051(99)00038-6

Cited by 16 publications

(6 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Architectural approaches to state recognition modeling vary widely, including control theory, signal processing, symbolic reasoning, decision-theory, and Bayesian networks. A variety of sensing options have also been explored including speech [17], [38], physical interaction [15], pupil size [36] and fovea location. New research is currently underway exploring more sophisticated bio-sensors [35], such as EEG, heart rate, plethysmography, and galvanic skin response [32].…”

Section: User Modeling Provides Adaptive Controlmentioning

confidence: 99%

Using GOMS and Bayesian plan recognition to develop recognition models of operator behavior

Zaientz¹,

DeKoven²,

Piegdon³

et al. 2006

SPIE Proceedings

View full text Add to dashboard Cite

Trends in combat technology research point to an increasing role for uninhabited vehicles in modern warfare tactics. To support increased span of control over these vehicles human responsibilities need to be transformed from tedious, errorprone and cognition intensive operations into tasks that are more supervisory and manageable, even under intensely stressful conditions. The goal is to move away from only supporting human command of low-level system functions to intention-level human-system dialogue about the operator's tasks and situation.A critical element of this process is developing the means to identify when human operators need automated assistance and to identify what assistance they need. Toward this goal, we are developing an unmanned vehicle operator task recognition system that combines work in human behavior modeling and Bayesian plan recognition. Traditionally, human behavior models have been considered generative, meaning they describe all possible valid behaviors. Basing behavior recognition on models designed for behavior generation can offers advantages in improved model fidelity and reuse. It is not clear, however, how to reconcile the structural differences between behavior recognition and behavior modeling approaches.Our current work demonstrates that by pairing a cognitive psychology derived human behavior modeling approach, GOMS, with a Bayesian plan recognition engine, ASPRN, we can translate a behavior generation model into a recognition model. We will discuss the implications for using human performance models in this manner as well as suggest how this kind of modeling may be used to support the real-time control of multiple, uninhabited battlefield vehicles and other semi-autonomous systems.

show abstract

Section: User Modeling Provides Adaptive Controlmentioning

confidence: 99%

Using GOMS and Bayesian plan recognition to develop recognition models of operator behavior

Zaientz¹,

DeKoven²,

Piegdon³

et al. 2006

SPIE Proceedings

View full text Add to dashboard Cite

show abstract

“…This is because contextual and environmental conditions can limit normal user capabilities. For example, the READY prototype considers how users react when under time pressure or cognitive load (e.g., distracted by having to navigate while walking versus sitting) [7,8]. Researchers found that individuals under time pressure alone actually produce fewer spoken disfluencies; but when they are navigating through a space (e.g., an airport), which is when they are distracted or under higher cognitive load, more are produced.…”

Section: Augmented Memorymentioning

confidence: 99%

Universal multimedia information access

Maybury

2003

Universal Access in the Information Society

View full text Add to dashboard Cite

Efficient, effective and intuitive access to multimedia information is essential for business, education, government and leisure. Unfortunately, interface design typically does not account for users with disabilities, estimated at 40 million in America alone. Given broad societal needs, our community has a social responsibility to provide universal designs that ensure efficient and effective access for all to heterogeneous and increasingly growing repositories of global information. This article describes information access functions, discusses associated grand challenges, and outlines potential benefits of technologies that promise to increase overall accessibility and success of interaction with multimedia. The article concludes by projecting the future of multimodal technology via a roadmap of multimodal resources, methods, and systems from 2003 through 2006.

show abstract

“…Bayesian Networks (Pearl, 1988) have been used for dealing with uncertainty in plans inference and offer a promising approach for plan recognition in situations where enough training data can be collected. Dynamic Belief Networks are also used as they capture the influence of temporal aspects (Jameson et al, 1999). On the other hand, there are a few problems in plan recognition for user modelling.…”

Section: Plan Recognitionmentioning

confidence: 99%

Designing computational models of collaborative learning interaction

Jermann¹,

Mühlenbrock²,

Soller³

2002

Proceedings of the Conference on Computer Support for Collaborative Learning Foundations for a CSCL Community - CSCL '02

View full text Add to dashboard Cite

A model and a pattern for data collection on collaborative actions in CSCL systems 31 Martin Mühlenbrock A computational model to differentiate between action and interaction in shared workspaces 37 Dan Suthers Implications of shared representations for computational modeling 42 A process to analyze interactions in collaborative systems with text-based computer mediated communication tools 65 E. J. R. de Castro, G. M. da Nóbrega, E. Ferneda, S. A. Cerri, and F. Lima Towards interaction modelling of asynchronous collaborative model-based learning 71Katrin Gassner Using patterns to reveal e-mail communication structures 77Abstract: Computational models of collaborative learning interaction provide functional computer-based representations that help us understand, explain, and predict patterns of group behavior, and support group learning processes. These models may assist students and teachers in managing and guiding the interaction during learning activities. In this paper, we introduce the proceedings of the 2 nd International Workshop on Designing Support for Collaborative Learning Interaction by exploring the advantages, implications, and support possibilities afforded by various types of computational models, in the context of a conceptual framework that we have developed.

show abstract

Making systems sensitive to the user's changing resource limitations

Cited by 16 publications

References 15 publications

Using GOMS and Bayesian plan recognition to develop recognition models of operator behavior

Using GOMS and Bayesian plan recognition to develop recognition models of operator behavior

Universal multimedia information access

Designing computational models of collaborative learning interaction

Contact Info

Product

Resources

About