The Predictive Performance Optimizer: An Adaptive Analysis Cognitive Tool for Performance Prediction
| Autor: | Tiffany S. Jastrzembski, Stuart Rodgers, Kevin A. Gluck |
|---|---|
| Rok vydání: | 2009 |
| Předmět: |
Computer science
business.industry Testbed Stability (learning theory) Experimental data Machine learning computer.software_genre Mesa Variety (cybernetics) Scheduling (computing) Medical Terminology Cognitive tools Performance prediction Artificial intelligence business computer Medical Assisting and Transcription computer.programming_language |
| Zdroj: | Proceedings of the Human Factors and Ergonomics Society Annual Meeting. 53:1642-1646 |
| ISSN: | 1071-1813 2169-5067 |
| DOI: | 10.1177/154193120905302102 |
| Popis: | The overarching goal of our research is to translate basic cognitive science into an applied, state-of-the-art cognitive tool. We have developed the Predictive Performance Optimizer (PPO) to provide teachers, trainers, and learners of all types with a new generation of adaptive training assistance, which seeks to capture and dynamically assess performance effectiveness, accurately predict future performance, and prescribe the scheduling of training events to enhance learning stability and maximize retention. This software tool functions according to an underlying mathematical model we have proposed (Jastrzembski, Gluck, & Gunzelmann, 2006), matured, and made more robust through careful validation across a variety of domains and contexts – scaling from laboratory experimental data available from the psychological literature to increasingly complex and militarily relevant team and pilot data measured from the F-16 simulator research in Mesa's Distributed Missions Operations testbed (Schreiber & Bennett, 2006). The predictive model captures learning signatures and mathematical regularities from the human memory system through calibration of learning and decay parameters using historical performance data, and then extrapolates those unique learning signatures to make predictions of performance at later dates in time, and across future potential regimen pathways. Of critical importance, the model explicitly accounts for the effects of temporal distribution of training on learning – a well-documented phenomenon known as the spacing effect – which reveals that given two training regimens of equal length and equal amounts of training opportunities, learning is more stable when practice events are spaced further apart in time. Incorporation of this effect allows PPO to generate precise, quantitative measures of retention stability as a function of how training events are spaced. Additional PPO capabilities allow users to immediately and dynamically assess how well projected regimens will meet performance effectiveness goals, stay within projected training budgets, and allow for maximum learning stability at distant points in time. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|