US 12,190,525 B2
Systems and methods of aviation data communication anomaly detection, as in air traffic control surveillance systems
Mark Rahmes, Melbourne, FL (US); Jennifer Spicer, Westminster, MD (US); Robert Konczynski, Melbourne, FL (US); Kusay Rukieh, Seffner, FL (US); Jody Flieder, West Melbourne, FL (US); Dustin Ellsworth, Fredonia, KY (US); Michael Fischer, Indialantic, FL (US); and Timothy Bruce Faulkner, Palm Bay, FL (US)
Assigned to L3Harris Technologies, Inc., Melbourne, FL (US)
Filed by L3Harris Technologies, Inc., Melbourne, FL (US)
Filed on Dec. 15, 2021, as Appl. No. 17/552,074.
Prior Publication US 2023/0186482 A1, Jun. 15, 2023
Int. Cl. G06V 10/26 (2022.01); G06T 7/13 (2017.01); G06V 10/44 (2022.01); G06V 10/46 (2022.01); G08G 5/00 (2006.01)
CPC G06T 7/13 (2017.01) [G06V 10/26 (2022.01); G06V 10/457 (2022.01); G06V 10/462 (2022.01); G06V 10/476 (2022.01); G08G 5/0004 (2013.01); G08G 5/0073 (2013.01); G06T 2207/10028 (2013.01)] 30 Claims
OG exemplary drawing
 
1. An aviation data communication anomaly detection system, comprising:
a plurality of interconnected aviation data communication devices, at least a portion of the plurality of the devices generating device status information; and
a processor in communication with at least one of the devices of the portion of the plurality of the devices and receiving the device status information, the processor operating a variational autoencoder that
receives the device status information;
optimizes the received device status information; and
determines or enables a user to determine whether the device status information qualifies as an anomaly that requires a response,
wherein the processor compares the optimized device status information to at least one of non-anomalous device status data or anomalous device status data in a latent space of the variational autoencoder, and
wherein the processor optimizes the device status information by generating a plurality of probabilistic models of the device status information and determining which of the plurality of models is optimal, and
wherein the processor determines which of the plurality of models is optimal by applying a linear program game theoretic optimization to the plurality of models and selecting which of the plurality of models to use to generate the n-D point scatter plot in latent space, and
wherein the plurality of models includes at least two of Adam, SGDM, or RMSProp.