Data mining of air traffic control operational errors

PDFProceedingsData miningAir traffic controlHuman errorBrown University. Center for the Study of Race and Ethnicity in AmericaNazeri, ZohrehNTL-AVIATION-AVIATIONNTL-AVIATION-Air Traffic ControlNTL-AVIATION-Aviation Human FactorsNTL-AVIATION-Aviation Safety/AirworthinessNTL-SAFETY AND SECURITY-Aviation Safety/AirworthinessNTL-SAFETY AND SECURITY-Human FactorsNTL-SAFETY AND SECURITY-SAFETY AND SECURITYNTL-REFERENCES AND DIRECTORIES-StatisticsBTS Data DirectoryIn this paper we present the results ofapplying data mining techniques to identify patterns andanomalies in air traffic control operational errors (OEs).Reducing the OE rate is of high importance and remains achallenge in the aviation safety community. Existingstudies, which use traditional methods and focus onindividual aspects of OEs, are limited to operations at asingle facility, or events in a short period of time. A holisticstudy of historical data available on OEs has not beenconducted. We have applied an attribute focusingtechnique to study 15 years of operational errors at allFAA Air Route Traffic Control Centers (ARTCCs) 1 in theNational Airspace System (NAS) in the U.S. We havefound \ue2\u20ac\u2dcinteresting\ue2\u20ac\u2122 patterns of common characteristics,anomalies, and changes in trends of operational errors.We interpreted the results with the help of domain expertsand plan to do a similar analysis for OEs at other types ofair traffic control facilities (towers and TRACONs) as well