Granted Patent B2

US 12,542,062 · App. 19/071,196 · Granted Feb 3, 2026

Inventors: David William Kleinbeck (Lees Summit, MO); Armando Montalvo (Winter Garden, FL)

Assignee: Digital Global Systems, Inc.

G08G5/22G01S3/043G01S3/046G01S3/46G06N3/08G06N7/01G08G5/55G08G5/57

Abstract

Claims (28)

1 . An apparatus for signal identification in a radiofrequency (RF) environment, comprising:

a plurality of node devices each including a processor;

wherein the plurality of node devices are operable to determine frequency-domain RF signal data from the RF environment;

wherein the plurality of node devices are operable to average the frequency-domain RF signal data into at least one tile;

wherein the at least one tile is visually represented as at least one waterfall image;

wherein the plurality of node devices are operable to utilize at least one convolutional neural network (CNN) to perform image analysis of the at least one waterfall image to classify at least one signal;

wherein the plurality of node devices are in network communication, comprising a group of networked nodes;

wherein the group of networked nodes is operable to collectively estimate at least one line of bearing and a geographical location for the at least one signal, creating at least one estimated geographical location; and

wherein the group of networked nodes is operable to collectively estimate a trajectory for the at least one signal based on the at least one estimated geographical location.

2 . The apparatus of claim 1 , wherein the at least one analyzed waterfall image includes a visual indication of the at least one signal.

3 . The apparatus of claim 2 , wherein the visual indication of the at least one signal is indicated with highlighting on the at least one waterfall image.

4 . The apparatus of claim 3 , further comprising a display operable to display the highlighting on the at least one waterfall image.

5 . The apparatus of claim 1 , wherein the at least one signal originates from a drone.

6 . The apparatus of claim 1 , wherein the image analysis of the at least one waterfall image using the at least one CNN includes a comparison of the at least one waterfall image to at least one other waterfall image.

7 . The apparatus of claim 6 , wherein the plurality of node devices are operable to update a database including the at least one other waterfall image with the at least one waterfall image.

8 . The apparatus of claim 1 , wherein the plurality of node devices are operable to transmit an alert related to the at least one signal.

9 . The apparatus of claim 1 , wherein the plurality of node devices are each in communication with at least one RF receiver operable to capture RF signal data and transform the RF signal data into the frequency-domain RF signal data using a Fast Fourier Transform (FFT).

10 . A method for signal analysis in a radiofrequency (RF) environment, comprising:

a plurality of node devices determining frequency-domain RF signal data from the RF environment;

the plurality of node devices averaging the frequency-domain RF signal data into at least one tile, wherein the at least one tile is represented as at least one waterfall image;

the plurality of node devices utilizing at least one convolutional neural network (CNN) to perform image analysis of the at least one waterfall image to classify at least one signal;

the plurality of node devices each networking with at least one other node device;

the plurality of node devices estimating at least one line of bearing and a geographical location for the at least one signal using the at least one other node device, creating at least one estimated geographical location; and

the plurality of node devices estimating a trajectory for the at least one signal based on the at least one estimated geographical location.

11 . The method of claim 10 , further comprising the plurality of node devices creating at least one analyzed waterfall image based on the identification of the at least one signal, wherein the at least one analyzed waterfall image includes a visual indication of the at least one signal.

12 . The method of claim 10 , wherein the plurality of node devices performing the image analysis of the at least one waterfall image using the at least one CNN to identify the at least one signal includes comparing the at least one waterfall image to at least one other waterfall image.

13 . The method of claim 12 , further comprising updating a database including the at least one other waterfall image with the at least one waterfall image.

14 . The method of claim 10 , wherein the plurality of node devices performing the image analysis of the at least one waterfall image using the at least one CNN to identify the at least one signal includes identifying a protocol.

Assignments (1)

Continuity (16)

References Cited (400)