A scalable human-in-the-loop decision support system has been built around an active learning algorithm operating on aircraft engine time series data. The system integrates hierarchical clustering and active learning algorithms backed by a big data analytics ecosystem with a browser-based user interface. This combination enables multiple expert users to efficiently train a model to classify aircraft engine behavior by prioritizing the segments of flight for human analysis. This system lowers the time required from human experts by eliminating unnecessary labelling effort and supporting the aircraft maintenance industry's service technicians.
Scalable human-in-the-loop decision support
2015-03-01
1479137 byte
Aufsatz (Konferenz)
Elektronische Ressource
Englisch
Improved decision support for engine-in-the-loop experimental design optimization
SAGE Publications | 2010
|Improved decision support for engine-in-the-loop experimental design optimization
Tema Archiv | 2010
|Improved decision support for engine-in-the-loop experimental design optimization
Online Contents | 2010
Improved decision support for engine-in-the-loop experimental design optimization
Online Contents | 2009
|Improved decision support for engine-in-the-loop experimental design optimization
Kraftfahrwesen | 2010
|