Name
Abstract | ||
|---|---|---|
Real-time monitoring with cognitive models offers the unique ability to both predict performance decrements from behavioral data and identify the responsible cognitive mechanisms for targeted interventions. However, their potential has not been realized because current parameter updating methods are prohibitively slow. We present a paradigm that enables real-time monitoring using cognitive models and demonstrate its implementation with a fatigue-sensitive task. In this demonstration, an operator workstation, a cognitive model, and a monitoring station are networked such that task performance data are sent to a central server that estimates model parameters and generates model-based performance metrics. These are sent to a monitoring station where they are summarized graphically together with model fit diagnostics. This constitutes an infrastructure that can be leveraged for future predictive adaptive system designs. |
Year | DOI | Venue |
|---|---|---|
2016 | 10.1007/978-3-319-39955-3_28 | HCI |
Keywords | Field | DocType |
Cognitive augmentation, Real-time monitoring, Parameter estimation, Fatigue, ACT-R, Computational cognitive models | Adaptive system,Computer science,Workstation,Behavioral data,Artificial intelligence,Operator (computer programming),Estimation theory,Cognitive model,Cognition,Machine learning | Conference |
Volume | ISSN | Citations |
9743 | 0302-9743 | 4 |
PageRank | References | Authors |
0.47 | 1 | 5 |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Leslie M. Blaha | 1 | 43 | 6.51 |
| Christopher R. Fisher | 2 | 4 | 0.47 |
| Matthew M. Walsh | 3 | 11 | 4.75 |
| Bella Z. Veksler | 4 | 6 | 1.97 |
| Glenn Gunzelmann | 5 | 105 | 20.14 |