Abstract
Developing a Cognitive Battery for Top-Down Workload Assessment
Frontiers in human neuroscience, v 12
2018
Abstract
Computational models of workload are often specialized to specific types of tasks and do not transfer between tasks. Part of this is due to the reliance of building models based on similar training tasks that enable detection of comparable neural indicators. As such, many workload prediction systems currently rely on tasks of similar design and interaction targeting specific cognitive functions. To address this, we developed personalized models in our study from a battery of standard cognitive tasks and mapped them to a dynamic operational environment, requiring simultaneous use of a combination of these cognitive functions.
Metrics
31 Record Views
Details
- Title
- Developing a Cognitive Battery for Top-Down Workload Assessment
- Creators
- Amanda Kraft - Lockheed Martin (United States)Matthias Ziegler - Lockheed Martin (United States)Sophia Mayne-DeLuca - Lockheed Martin (United States)Trevor Sands - Lockheed Martin (United States)Alison Perez - Lockheed Martin (United States)Jesse Mark - Drexel University, School of Biomedical Engineering, Science, and Health SystemsAdrian Curtin - Drexel University, School of Biomedical Engineering, Science, and Health SystemsAmanda Sargent - Drexel University, School of Biomedical Engineering, Science, and Health SystemsHasan Ayaz - Drexel University, School of Biomedical Engineering, Science, and Health SystemsWilliam Casebeer - Lockheed Martin (United States)
- Publication Details
- Frontiers in human neuroscience, v 12
- Conference
- The 2nd International Neuroergonomics Conference (Philadelphia, Pennsylvania, United States, 27 Jun 2018–29 Jun 2018)
- Resource Type
- Abstract
- Language
- English
- Academic Unit
- School of Biomedical Engineering, Science, and Health Systems
- Other Identifier
- 991019186656404721