Granted Patent B1

US 12,207,119 · App. 18/920,175 · Granted Jan 21, 2025

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

Assignee: Digital Global Systems, Inc.

H04W24/08H04B17/20H04B17/23H04B17/26H04B17/27H04B17/29H04B17/309H04B17/318H04W24/10H04B17/24H04W24/04

Abstract

Claims (60)

1. An apparatus for signal detection in an electromagnetic environment, comprising:

at least one receiver, at least one processor, and at least one memory;

wherein the apparatus is operable to create power level measurements of the electromagnetic environment;

wherein the apparatus is operable to reveal and/or classify at least one signal based on an identification and/or a classification algorithm;

wherein the identification and/or classification algorithm are operable to identify temporal features in real time;

wherein the apparatus includes a temporal feature extraction (TFE) function;

wherein the TFE function is operable to create impressions of the electromagnetic environment based on at least one machine learning (ML) algorithm;

wherein the TFE function is operable to identify at least one narrowband signal and at least one wideband signal in a same frequency and hidden by a second wideband signal based on historical data;

wherein the apparatus is operable to calculate a first derivative of the power level measurements and a second derivative of the power level measurements;

wherein the apparatus is operable to process signal data using compressed data for deltas;

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

wherein the apparatus is operable to reconstruct the at least one signal using the deltas and the at least one baseline.

2. The apparatus of claim 1 , further comprising a multiplicity of receivers, wherein the multiplicity of receivers is operable to monitor multiple bandwidths and perform time-frequency analyses at the same time.

3. The apparatus of claim 1 , wherein the apparatus is operable to use two smoothing filters to create a calibration vector to de-bias raw signal data.

4. The apparatus of claim 1 , wherein the identification and/or classification algorithm is operable to match the at least one signal with at least one signal that it had identified during a learning phase of the at least one ML algorithm.

5. The apparatus of claim 1 , wherein the apparatus is mobile and linked to a Global Positioning System (GPS) system for time and location.

6. The apparatus of claim 1 , wherein the apparatus is operable to estimate a location of a signal emitting device from which the at least one signal is emitted based on in-phase and quadrature (I/Q) data generated from a spectral sweep.

7. The apparatus of claim 1 , wherein the apparatus is operable to fill gaps during reconstruction of the at least one signal where data of the at least one signal is absent.

8. The apparatus of claim 1 , wherein the apparatus is operable to form a knowledge map of the electromagnetic environment based on the power level measurements of the electromagnetic environment.

9. The apparatus of claim 8 , wherein the at least one ML algorithm utilizes an artificial neural network (ANN).

10. The apparatus of claim 1 , wherein the apparatus is operable to detect the at least one signal in the electromagnetic environment based on matched positive and negative gradients.

11. A method for signal detection in an electromagnetic environment, comprising:

creating power level measurements of the electromagnetic environment;

forming a knowledge map of the electromagnetic environment based on the power level measurements of the electromagnetic environment;

determining at least one baseline;

subtracting the at least one baseline from a spectral sweep to reveal at least one signal to create signal data;

classifying the at least one signal based on a classification algorithm;

wherein the classification algorithm is operable to identify temporal features in real time;

using two smoothing filters to create a calibration vector to de-bias raw signal data;

calculating a first derivative of the power level measurements and a second derivative of the power level measurements;

creating impressions of the electromagnetic environment over time using a temporal feature extraction (TFE) function based on at least one machine learning (ML) algorithm, and interpreting the impressions as the at least one signal;

processing the signal data using compressed data for deltas;

identifying at least one narrowband signal and at least one wideband signal in a same frequency of and hidden by a second wideband signal based on historical data; and

reconstructing the at least one signal using the deltas and the at least one baseline;

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

12. The method of claim 11 , further comprising filling gaps during reconstruction of the at least one signal where data of the at least one signal is absent.

13. The apparatus of claim 11 , wherein the classification algorithm is operable to match the at least one signal with at least one second signal that it had identified during a learning phase of the at least one ML algorithm.

14. A method for signal detection in an electromagnetic environment, comprising:

scrubbing a spectral sweep against a knowledge map of the electromagnetic environment;

smoothing the spectral sweep with a correction vector;

detecting at least one signal in the electromagnetic environment;

determining at least one baseline;

subtracting the at least one baseline from the spectral sweep to reveal the at least one signal to create signal data;

classifying the at least one signal based a classification algorithm;

wherein the classification algorithm is operable to identify temporal features in real time;

using two smoothing filters to create a calibration vector to de-bias raw signal data;

calculating a first derivative of power level measurements of the electromagnetic environment and a second derivative of the power level measurements;

creating impressions of the electromagnetic environment over time using a temporal feature extraction (TFE) function based on at least one machine learning (ML) algorithm, and interpreting the impressions as the at least one signal;

wherein the at least one ML algorithm utilizes an artificial neural network (ANN);

processing the signal data using compressed data for deltas;

reconstructing the at least one signal using the deltas and the at least one baseline; and

creating a profile of the electromagnetic environment based on the knowledge map and the at least one ML algorithm;

wherein the profile comprises a highest value of the power level measurements at each frequency during a predetermined period; and

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

15. The method of claim 14 , further comprising extracting at least one time-frequency feature from the knowledge map.

16. The method of claim 14 , wherein the TFE function is operable to identify a narrowband signal and at least one wideband signal in a same frequency of a second wideband signal based on historical data.

17. The method of claim 14 , wherein the classification algorithm is operable to match the at least one signal with at least one second signal that it had identified during a learning phase of the machine learning algorithm.

18. The method of claim 14 , further comprising filling gaps during reconstruction of the at least one signal where data of the at least one signal is absent.

19. The method of claim 14 , further comprising sending a notification and/or an alarm to at least one remote device after detecting the at least one signal.

20. The method of claim 14 , wherein detecting the at least one signal in the electromagnetic environment is based on matched positive and negative gradients.

Assignments (3)

Continuity (21)

References Cited (400)