Mining Aircraft Telemetry Data with Evolutionary Algorithms

The Ganged Phased Array Radar Risk Mitigation System (GPAR-RMS) was a mobile ground-based sense-and-avoid software and hardware system for Unmanned Aircraft System (UAS) operations developed by the University of North Dakota. The Risk Mitigation (RM) software subsystem for GPAR-RMS was designed to estimate the current risk of mid-air collision, between the Unmanned Aircraft (UA) and a General Aviation (GA) aircraft flying under Visual Flight Rules (VFR) in the surrounding airspace. The results of data mining an aircraft telemetry data set from a consecutive nine month period in 2011 are presented. This aircraft telemetry data set consisted of Flight Data Monitoring (FDM) data obtained from Garmin G1000 devices onboard Cessna 172 GA aircraft. Complex subpaths were discovered from the aircraft telemetry data set using a novel application of a novel application of an ant colony algorithm. Probabilistic models were then data mined from those subpaths using unsupervised learning algorithms.

Autorentext

Dr. Kirk Ogaard received his B.S. and M.S. degrees in computer science from the University of North Dakota (UND) in 1999 and 2008, respectively. He graduated with the first Ph.D. in scientific computing from UND in 2012. His postdoctoral research was at the U.S. Army Research Laboratory at Aberdeen Proving Ground, Maryland.

Klappentext

The Ganged Phased Array Radar Risk Mitigation System (GPAR-RMS) was a mobile ground-based sense-and-avoid software and hardware system for Unmanned Aircraft System (UAS) operations developed by the University of North Dakota. The Risk Mitigation (RM) software subsystem for GPAR-RMS was designed to estimate the current risk of mid-air collision, between the Unmanned Aircraft (UA) and a General Aviation (GA) aircraft flying under Visual Flight Rules (VFR) in the surrounding airspace. The results of data mining an aircraft telemetry data set from a consecutive nine month period in 2011 are presented. This aircraft telemetry data set consisted of Flight Data Monitoring (FDM) data obtained from Garmin G1000 devices onboard Cessna 172 GA aircraft. Complex subpaths were discovered from the aircraft telemetry data set using a novel application of a novel application of an ant colony algorithm. Probabilistic models were then data mined from those subpaths using unsupervised learning algorithms.