IP Library › Granted Patent US 12,443,865
Granted Patent B2
US 12,443,865 · App. 17/814,932 · Granted Oct 14, 2025

Automatic dependent surveillance broadcast (ADS-B) system providing anomaly detection and related methods

Inventors: Mark D. Rahmes (Melbourne, FL); Kevin L. Fox (Palm Bay, FL); Gran Roe (Melbourne, FL); Christopher Jason Berger (Leesburg, VA); Ralph Smith (Oak Hill, VA); Timothy B. Faulkner (Palm Bay, FL); Robert Konczynski (Melbourne, FL); Kevin R. Niewoehner (Stafford, VA)
Assignee: EAGLE TECHNOLOGY, LLC
G06N5/042G06N7/01G08G5/22
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 12,443,865
App. No.
17/814,932
Granted
Oct 14, 2025
Kind
B2
Abstract

An Automatic Dependent Surveillance Broadcast (ADS-B) system may include a plurality of ADS-B terrestrial stations, with each ADS-B terrestrial station comprising an antenna and wireless circuitry associated therewith defining a station gain pattern. The system may further include a controller including a variational autoencoder (VAE) configured to compress station pattern data from the plurality of ADS-B terrestrial stations, create a normal distribution of the compressed data in a latent space of the VAE, and decompress the compressed station pattern data from the latent space. The controller may also include a processor coupled to the VAE and configured to process the decompressed station pattern data using a probabilistic model selected from among different probabilistic models based upon a game theoretic reward matrix, determine an anomaly from the processed decompressed station pattern data, and generate an alert (e.g., a station specific alert) based upon the determined anomaly.

Claims (46)

1. An Automatic Dependent Surveillance Broadcast (ADS-B) system comprising:

a plurality of ADS-B terrestrial stations, each ADS-B terrestrial station comprising an antenna and wireless circuitry associated therewith defining a station gain pattern; and

a controller comprising

a variational autoencoder (VAE) configured to

compress station gain pattern data from the plurality of ADS-B terrestrial stations,

create a normal distribution of the compressed data in a latent space of the VAE, and

decompress the compressed station pattern data from the latent space; and

a processor coupled to the VAE and configured to

process the decompressed station pattern data using a probabilistic model selected from among a plurality of different probabilistic models based upon a game theoretic reward matrix,

determine an anomaly from the processed decompressed station pattern data, and

generate an alert based upon the determined anomaly.

2. The ADS-B system of claim 1 wherein the VAE is configured to compress the station pattern data with a first set of weights, and decompress the compressed station pattern data with a second set of weights different than the first set of weights.

3. The ADS-B system of claim 2 wherein the processor is configured to update at least one of the first and second sets of weights based upon a loss detected in the processed decompressed station pattern data.

4. The ADS-B system of claim 1 wherein the station gain pattern corresponds to different radio frequency (RF) channels.

5. The ADS-B system of claim 1 wherein the processor is configured to process the decompressed station pattern data using the probabilistic model based upon historical gain pattern data for respective antennas.

6. The ADS-B system of claim 1 wherein the plurality of different probabilistic models comprises at least one of ADAM, Stochastic Gradient Descent with Momentum (SGDM), and RMSProp deep learning models.

7. The ADS-B system of claim 1 wherein the alert comprises a service alert for service to be performed at a corresponding ADS-B terrestrial station having the determined anomaly.

8. A controller for an Automatic Dependent Surveillance Broadcast (ADS-B) system, the controller comprising:

a variational autoencoder (VAE) configured to

compress station gain pattern data from a plurality of ADS-B terrestrial stations, each ADS-B terrestrial station comprising an antenna and wireless circuitry associated therewith defining a station gain pattern,

create a normal distribution of the compressed data in a latent space of the VAE, and

decompress the compressed station pattern data from the latent space; and

a processor coupled to the VAE and configured to

process the decompressed station pattern data using a probabilistic model selected from among a plurality of different probabilistic models based upon a game theoretic reward matrix,

determine an anomaly from the processed decompressed station pattern data, and

generate an alert based upon the determined anomaly.

9. The controller of claim 8 wherein the VAE is configured to compress the station pattern data with a first set of weights, and decompress the compressed station pattern data with a second set of weights different than the first set of weights.

10. The controller of claim 9 wherein the processor is configured to update at least one of the first and second sets of weights based upon a loss detected in the processed decompressed station pattern data.

11. The controller of claim 8 wherein the station gain pattern corresponds to different radio frequency (RF) channels.

12. The controller of claim 8 wherein the processor is configured to process the decompressed station pattern data using the probabilistic model based upon historical gain pattern data for respective antennas.

13. The controller of claim 8 wherein the plurality of different probabilistic models comprises at least one of ADAM, Stochastic Gradient Descent with Momentum (SGDM), and RMSProp deep learning models.

14. The controller of claim 8 wherein the alert comprises a service alert for service to be performed to the antenna.

15. A method for operating an Automatic Dependent Surveillance Broadcast (ADS-B) system, the method comprising:

using a variational autoencoder (VAE) for

compressing station gain pattern data from a plurality of ADS-B terrestrial stations, each ADS-B terrestrial station comprising an antenna and wireless circuitry associated therewith defining a station gain pattern,

creating a normal distribution of the compressed data in a latent space of the VAE, and

decompressing the compressed station pattern data from the latent space; and

using a processor for

processing the decompressed station pattern data using a probabilistic model selected from among a plurality of different probabilistic models based upon a game theoretic reward matrix,

determining an anomaly from the processed decompressed station pattern data, and

generating an alert based upon the determined anomaly.

16. The method of claim 15 wherein compressing comprises compressing the station pattern data with a first set of weights, and decompressing comprises decompressing the compressed station pattern data with a second set of weights different than the first set of weights.

17. The method of claim 16 comprising updating at least one of the first and second sets of weights based upon a loss detected in the processed decompressed station pattern data.

18. The method of claim 15 wherein the station gain pattern corresponds to different radio frequency (RF) channels.

19. The method of claim 15 wherein processing comprises processing the decompressed station pattern data using the probabilistic model based upon historical gain pattern data for respective antennas.

20. The method of claim 15 wherein the plurality of different probabilistic models comprises at least one of ADAM, Stochastic Gradient Descent with Momentum (SGDM), and RMSProp deep learning models.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Jul 27, 2022
From: RAHMES, MARK D.; FOX, KEVIN L.; ROE, GRAN; BERGER, CHRISTOPHER JASON; SMITH, RALPH; FAULKNER, TIMOTHY B.; KONCZYNSKI, ROBERT; NIEWOEHNER, KEVIN R.
To: EAGLE TECHNOLOGY, LLC
Reel/Frame 060644/0406 →
Continuity (1)
Related Publication 20240037426A1 · Feb 1, 2024
References Cited (65)
US 10181185B2 · Park et al. · 2019 [cited by applicant]
US 10248742B2 · Desell et al. · 2019 [cited by applicant]
US 10373056B1 · Andoni et al. · 2019 [cited by applicant]
US 10410113B2 · Clayton et al. · 2019 [cited by applicant]
US 10528533B2 · Saini et al. · 2020 [cited by applicant]
US 10593033B2 · Niculescu-Mizil et al. · 2020 [cited by applicant]
US 10600009B1 · Augustine et al. · 2020 [cited by applicant]
US 10616257B1 · Soulhi et al. · 2020 [cited by applicant]
US 10665251B1 · Wood, III et al. · 2020 [cited by applicant]
US 10679129B2 · Baker · 2020 [cited by applicant]
US 10733722B2 · Niculescu-Mizil et al. · 2020 [cited by applicant]
US 10743809B1 · Kamousi et al. · 2020 [cited by applicant]
US 10789703B2 · Lu et al. · 2020 [cited by applicant]
US 10812523B2 · Latapie et al. · 2020 [cited by applicant]
US 10817394B2 · Oba · 2020 [cited by applicant]
US 10839320B2 · Augustine et al. · 2020 [cited by applicant]
US 10848508B2 · Chen et al. · 2020 [cited by applicant]
US 10860928B2 · Mnih et al. · 2020 [cited by applicant]
US 10872209B2 · Ha et al. · 2020 [cited by applicant]
US 10880763B1 · Vela et al. · 2020 [cited by applicant]
US 10909419B2 · Itou et al. · 2021 [cited by applicant]
US 10909671B2 · Kimura et al. · 2021 [cited by applicant]
US 10931700B2 · Soulhi et al. · 2021 [cited by applicant]
US 10964011B2 · Cosatto et al. · 2021 [cited by applicant]
US 10970395B1 · Bansal et al. · 2021 [cited by applicant]
US 20030018928A1 · James et al. · 2003 [cited by applicant]
US 20190377870A1 · Daniel et al. · 2019 [cited by applicant]
US 20200183047A1 · Denli et al. · 2020 [cited by applicant]
US 20200193418A1 · Augustine et al. · 2020 [cited by applicant]
US 20200342362A1 · Soni et al. · 2020 [cited by applicant]
US 20210065070A1 · Augustine et al. · 2021 [cited by applicant]
US 20220021477A1 · Ge · 2022 [cited by examiner]
US 20220060235A1 · Namgoong · 2022 [cited by examiner]
US 20220091275A1 · Held et al. · 2022 [cited by applicant]
US 20220321961A1 · Hama · 2022 [cited by examiner]
US 20230007530A1 · Vitthaladevuni · 2023 [cited by examiner]
US 20230090593A1 · Kim · 2023 [cited by examiner]
US 20240202542A1 · Lindbom · 2024 [cited by examiner]
Fox et al. “Utilizing sinthetic data for VV&C of machine learning applications” 2022 Integrated Communications Navigation and Surveillance (ICNS) Conference Apr. 5-7, 2022; pp. 14. [cited by applicant]
Amini et al. “Variational Autoencoder for End-To-End Control of Autonomous Driving With Novelty Detection and Training De-Biasing” 2018 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS): Oct. 20… [cited by applicant]
An et al. “Variational Autoencoder Based Anomaly Detection Using Reconstruction Probability” Special Lecture on IE: 2(1) 2015; pp. 1-18. [cited by applicant]
Chen et al. “Unsupervised Anomaly Detection of Industrial Robots Using Sliding-Window Convolutional Variational Autoencoder” IEEE Access, 8, 2020: 47072-47081. [cited by applicant]
Daudt et al. “Urban Change Detection for Multispectral Earth Observation Using Convolutional Neural Networks” In IEEE International Geoscience and Remote Sensing Symposium (IGARSS): Jul. 2018; pp. 2115-2118. [cited by applicant]
Fan et al. “Video Anomaly Detection and Localization via Gaussian Mixture Fully Convolutional Variational Autoencoder” Computer Vision and Image Understanding: (2020) 195, 102920; pp. 13. [cited by applicant]
Gong et al. “Memorizing Normality to Detect Anomaly: Memory-Augmented Deep Autoencoder for Unsupervised Anomaly Detection” In Proceedings of the IEEE/CVF International Conference on Computer Vision: 2019; pp. 1705-1714. [cited by applicant]
Kawachi et al. “Complementary Set Variational Autoencoder for Supervised Anomaly Detection” In 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP): Apr. 2018; pp. 2366-2370; Abstract O… [cited by applicant]
Kingma et al. Auto-Encoding Variational Bayes arXiv preprint arXiv:1312.6114 https://arxiv.org/abs/1312.6114: Dec. 2013; pp. 14. [cited by applicant]
Lecun et al. “The MNIST Database of Handwritten Digits” http://yann.lecun.com/exdb/mnist retrieved from internet Jul. 15, 2022; pp. 6. [cited by applicant]
Li et al. “Anomaly Detection of Time Series With Smoothness-Inducing Sequential Variational Auto-Encoder” IEEE transactions on neural networks and learning systems: 2020; pp. 15. [cited by applicant]
Memarzadeh et al. “Unsupervised Anomaly Detection in Flight Data Using Convolutional Variational Auto-Encoder” Aerospace 2020, 7(8), 115; pp. 19. [cited by applicant]
Nguyen et al. “GEE: A Gradient-based Explainable Variational Autoencoder for Network Anomaly Detection” https://arxiv.org/abs/1903.06661; Mar. 15, 2019; pp. 10. [cited by applicant]
Norlander et al. “Latent Space Conditioning for Improved Classification and Anomaly Detection” https://www.semanticscholar.org/paper/Latent-space-conditioning-for-improved-and-anomaly-Norlander-Sopasakis/d0edbd735bd1083… [cited by applicant]
Sun et al. “Learning Sparse Representation With Variational Auto-Encoder for Anomaly Detection” IEEE Access, 6, 2018; pp. 33353-33361. [cited by applicant]
Wang et al. “Deep Learning for Anomaly Detection” In Proceedings of the 13th International Conference on Web Search and Data Mining: Jan. 2020; pp. 894-896. [cited by applicant]
Wiewel et al. “Continual Learning for Anomaly Detection With Variational Autoencode” In IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP): May 2019; pp. 3837-3841. Abstract Only. [cited by applicant]
Xu et al. “Unsupervised Anomaly Detection via Variational Auto-Encoder for Seasonal KPIs in Web Applications” In Proceedings of the 2018 World Wide Web Conference: Apr. 2018; pg. [cited by applicant]
Yan et al. “Abnormal Event Detection From Videos Using a Two-Stream Recurrent Variational Autoencoder” IEEE Transactions on Cognitive and Developmental Systems, 12(1) Nov. 25, 2018; pp. 30-42. [cited by applicant]
Yao et al. “Unsupervised Anomaly Detection Using Variational Auto-Encoder Based Feature Extraction” In 2019 IEEE International Conference on Prognostics and Health Management (ICPHM): Jun. 2019; Abstract Only. [cited by applicant]
Zavrak et al. “Anomaly-based intrusion detection from network flow features using variational autoencoder” IEEE Access, 8: Jun. 2020; pp. 13. [cited by applicant]
Zerrouki et al. “Desertification Detection Using an Improved Variational Autoencoder-Based Approach Through ETM-Landsat Satellite Data” IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 1… [cited by applicant]
Zimmerer et al “Context-Encoding Variational Autoencoder for Unsupervised Anomaly Detection” Medical Imaging with Deep Learning 2019: https://arxiv.org/abs/1907.12258 arXiv preprint arXiv:1812.05941: pp. 6. [cited by applicant]
Easa and Daedalean “Concepts of Design Assurance for Neural Networks (CoDANN) II Public Extract” EASA AI Task Force and Daedalean AG: 2021; pp. 113. [cited by applicant]
SAE International, On-Road Automated Driving (ORAD) Committee, “Taxonomy & Definitions for Operational Design Domain (ODD) for Driving Automation Systems J3259,” Jul. 15, 2021. [Online]. Available: https://www.sae.org/s… [cited by applicant]
Society of Automotive Engineers (SAE) “Surface Vehicle Recommended Practice” J3016; Apr. 2021; pp. 41. [cited by applicant]
Niewoehner et al. “Novel Framework to Advance Verification, Validation, and Certification of Non-Deterministic, AI-Based Algorithms for Safety Critical Applications” The Journal of Air Traffic Control, Fall 2021; vol. 6… [cited by applicant]