AI-Based Model to Identify Illegal Aircraft Behavior

This post is also available in: עברית (Hebrew)

A new technology would target small, non-commercial flyers classified as general aviation small aircraft, jets, ultralights and UAVs that could be involved in potential terror threats, drug smuggling, and other illegal activity.

The Department of Homeland Security (DHS) Science and Technology Directorate (S&T) is developing a Predictive Threat Model (PTM) to help Custom and Border Protection’s (CBP) Air and Marine Operations Center (AMOC) identify and stop nefarious aircraft.

The model uses data from past AMOC cases and artificial intelligence to identify certain behavior profiles of previously interdicted aircraft and predict future threats. Information such as location, radio signal, and flight destination, could be combined in the system to predict the intentions of a criminal aircraft, reports homelandprepnews.com.

The predictive solution deals with statistical artificial intelligence and machine learning capabilities, according to janesairport360.com. Basing on mining historical data from AMOC, the model uses Bayesian (statistical theory) inference algorithms to predict future threats. “Identifying certain behavior profiles of previously interdicted aircraft offers a surprisingly reliable measure for determining whether or not aircraft are a risk to national security,” S&T noted.

The model has accurately predicted suspect behaviors in testing at the AMOC. It has completed the initial prototype phase and is in now a six- to nine-month operational period during which it will undergo further enhancements and development. The third phase will be the final operational implementation at AMOC.