Granted Patent B2

US 12,302,146 · App. 18/646,210 · Granted May 13, 2025

Inventors: David William Kleinbeck (Lees Summit, MO); Ronald C. Dzierwa (Baltimore, MD); Daniel Carbajal (Severna Park, MD)

Assignee: Digital Global Systems, Inc.

H04W24/08H04B17/23H04B17/27H04B17/309H04B17/318H04W4/029H04W16/14H04W24/10H04W52/0203H04W64/006H04W72/0453H04W72/0473H04B17/3911

Abstract

Claims (63)

1. A system for spectrum data management for a radio frequency (RF) environment, comprising:

at least one receiver and an automatic signal detection (ASD) module;

wherein the ASD module includes machine learning;

wherein the system is operable to form a knowledge map based on past power level measurements of the RF environment over time;

wherein the system is operable to compare a real-time spectral sweep based on current power level measurements of the RF environment to the knowledge map;

wherein the system is operable to automatically detect and/or classify at least one signal from the RF environment based on the comparison of the real-time spectral sweep to the knowledge map;

wherein the system is operable to identify the at least one signal based in part upon whether a signal parameter of the at least one signal matches any signal parameters in a signal characteristic listing data in a database including hardware parameters;

wherein the hardware parameters include antenna position, antenna type, orientation, azimuth, gain, and/or equivalent isotropically radiated power (EIRP) for a transmitter associated with the at least one signal;

wherein the automatic detection of the at least one signal in the RF environment further comprises fine-tuning a threshold of power level on a segmented basis while extracting at least one temporal feature from the knowledge map;

wherein the system is operable to send an alert based on the at least one signal having a higher power than the past power level measurements of the knowledge map;

wherein the system is operable to determine a baseline based on an average of the past power level measurements with at least one signal of interest subtracted based on gradients;

wherein the system is operable to smooth the real-time spectral sweep with a correction vector, wherein the correction vector is determined according to the real-time spectral sweep;

wherein the system is operable to subtract the baseline from the real-time spectral sweep to reveal the at least one signal;

wherein the system is operable to process signal data using compressed data for deltas to generate processed data, and wherein the system is configured to detect at least one anomaly based on the processed data;

wherein the deltas are differentials from the baseline and minimize data sets or sample data required for comparisons and/or analytics; and

wherein the system is operable to generate at least one report for the RF environment.

2. The system of claim 1 , wherein the ASD module includes automatic signal variance determination.

3. The system of claim 1 , wherein the machine learning includes an artificial neural network (ANN).

4. The system of claim 1 , wherein the at least one receiver comprises a primary receiver and a secondary receiver, wherein the primary receiver is configured to generate In-Phase and Quadrature (I/Q) data for at least one target bandwidth based on a learning and conflict detection engine, and wherein the secondary receiver is configured to perform a fast Fourier transform (FFT) based on a wideband sweeping of the RF environment.

5. The system of claim 4 , further comprising an I/Q buffer, wherein the system is operable to determine whether to keep the I/Q data in the I/Q buffer.

6. The system of claim 4 , further comprising a demodulator configured to distill the I/Q data and store actionable I/Q data, wherein the actionable I/Q data comprises signal metrics, protocol data, radio identification (ID), network ID, and layer 3 data.

7. The system of claim 1 , wherein the system is configured for conflict recognition and anomaly identification.

8. The system of claim 1 , wherein the system is operable to tune the ASD module automatically.

9. The system of claim 1 , wherein the ASD module is operable for signal recognition based on temporal feature extraction.

10. The system of claim 1 , wherein the system is operable to use a calibration vector to de-bias raw signal data.

11. The system of claim 1 , wherein the system further comprises a learning and conflict detection engine.

12. A system for spectrum data management for a radio frequency (RF) environment, comprising:

at least one receiver;

wherein the system is operable to create learning data including power level measurements of the RF environment;

wherein the system is operable to create a knowledge map of the RF environment based on the learning data;

wherein the system is operable to compare a real-time spectral sweep based on the power level measurements of the RF environment to the knowledge map;

wherein the system is operable to detect at least one signal in the RF environment based on matched positive and negative gradients;

wherein the system is operable to include machine learning to detect the at least one signal;

wherein the system is operable to identify the at least one signal based in part upon whether a signal parameter of the at least one signal matches any signal parameters in a signal characteristic listing data in a database including hardware parameters;

wherein the hardware parameters include antenna position, antenna type, orientation, azimuth, gain, and/or equivalent isotropically radiated power (EIRP) for a transmitter associated with the at least one signal;

wherein the system is operable to determine a baseline based on the matched positive and negative gradients;

wherein the system is operable to smooth the real-time spectral sweep with a correction vector, wherein the correction vector is determined according to the real-time spectral sweep;

wherein the system is operable to use gradients from smoothed signal data to create a calibration vector;

wherein the system is operable to use the calibration vector to de-bias raw signal data;

wherein the system is operable to process signal data using compressed data for deltas to generate processed data, and wherein the system is configured to detect at least one anomaly based on the processed data;

wherein the deltas are differentials from the baseline and minimize data sets or sample data required for comparisons and/or analytics; and

wherein the system is operable to subtract the baseline from the real-time spectral sweep to reveal the at least one signal.

13. The system of claim 12 , wherein the machine learning includes automatic signal variance determination.

14. The system of claim 12 , wherein the machine learning includes an artificial neural network (ANN).

15. A method of spectrum data management for a radio-frequency (RF) environment, comprising:

a node device comprising at least one receiver and at least one automatic signal detection (ASD) module creating learning data including power level measurements of the RF environment;

wherein the ASD module includes machine learning software;

wherein a knowledge map of the RF environment is created based on the learning data;

the node device comparing a real-time spectral sweep of the RF environment based on the power level measurements of the RF environment to the knowledge map;

the node device detecting at least one signal in the RF environment based on matched positive and negative gradients;

the node device averaging the real-time spectral sweep, removing areas identified by the matched positive and negative gradients, and connecting points between removed areas to determine a baseline;

the node device identifying the at least one signal based in part upon whether a signal parameter of the at least one signal matches any signal parameters in a signal characteristic listing data in a database including hardware parameters;

the node device smoothing the real-time spectral sweep with a correction vector, wherein the correction vector is determined according to the real-time spectral sweep; and

the node device using gradients from smoothed signal data to create a calibration vector;

the node device using the calibration vector to de-bias raw signal data;

the node device subtracting the baseline from the real-time spectral sweep to reveal the at least one signal; and

the node device processing signal data using compressed data for deltas to create processed data and the node device detecting and identifying at least one anomaly based on the processed data;

wherein the hardware parameters include antenna position, antenna type, orientation, azimuth, gain, and/or equivalent isotropically radiated power (EIRP) for a transmitter associated with the at least one signal;

wherein the node device detecting the at least one signal in the RF environment further comprises fine-tuning a threshold of the power level measurements on a segmented basis while extracting at least one temporal feature from the knowledge map; and

wherein the deltas are differentials from the baseline and minimize data sets or sample data required for comparisons and/or analytics.

16. The method of claim 15 , further comprising the node device classifying the at least one signal based on machine learning software.

17. The method of claim 15 , further comprising the node device generating at least one report for the RF environment.

18. The method of claim 15 , further comprising the node device generating In-Phase and Quadrature (I/Q) data for at least one target bandwidth determined by a learning and conflict detection engine; the node device distilling the I/Q data and storing actionable I/Q data; and the node device performing a fast Fourier transform (FFT) based on a wideband sweeping of the RF environment and extracting meta data based on FFT data.

Assignments (3)

Continuity (29)

References Cited (400)