Nikunj Oza

Data-driven Anomaly Detection

Nikunj Oza

Talk: Data-driven Anomaly Detection

This talk will describe recent work by the NASA Data Sciences Group on data-driven anomaly detection applied to air traffic control over Los Angeles, Denver, and New York. This data mining approach is designed to discover operationally significant flight anomalies, which were not pre-defined. These methods are complementary to traditional exceedance-based methods, in that they are more likely to yield false alarms, but they are also more likely to find previously-unknown anomalies. We discuss the discoveries that our algorithms have made that exceedance-based methods did not identify.

Nikunj Oza

Nikunj Oza is the leader of the Data Sciences Group at NASA Ames Research Center. He also leads a NASA project team which applies data mining to aviation safety. Dr. Oza─ůs 40+ research papers represent his research interests which include data mining, machine learning, anomaly detection, and their applications to Aeronautics and Earth Science.