Granted Patent B2

US 12,177,701 · App. 18/633,977 · Granted Dec 24, 2024

Inventors: Daniel Carbajal (Severna Park, MD); Ronald C. Dzierwa (Baltimore, MD)

Assignee: Digital Global Systems, Inc.

H04W24/08H04L27/00H04L27/0006H04W16/14H04W64/006H04W72/0453H04W76/11H04W24/02

Abstract

Claims (71)

1. A method for automatic signal detection in an environment, comprising:

learning the environment, thereby creating learning data including power level measurements of one or more frequency bins within the environment;

forming a knowledge map of the environment based on the power level measurements of the one or more frequency bins within the environment;

creating a profile of the environment based on the knowledge map;

scrubbing a spectral sweep against the profile;

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

indexing the power level measurements of the one or more frequency bins in a spectrum section using a learning routine;

smoothing the spectral sweep with a correction vector and at least one first smoothing filter;

detecting at least one signal in the environment based on a machine learning algorithm;

wherein the machine learning algorithm includes signal variance determination from different locations and times;

performing an at least one second smoothing filter only on frequencies outside a frequency range of the at least one signal;

generating signal variance reports, power usage reports, radio frequency (RF) survey reports, and/or signal optimization reports;

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

creating a reconstructed signal using compressed data for deltas and the baseline;

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

wherein the learning data is based on demodulating and/or decoding the at least one signal;

wherein the deltas provide for signal identification, interference identification, neighboring band identification, device identification, and/or signal optimization; and

wherein creating the reconstructed signal includes filling gaps where data of the at least one signal is absent.

2. The method of claim 1 , wherein the detecting the at least one signal in the environment comprises fine-tuning a threshold of power level on a segmented basis.

3. The method of claim 1 , wherein smoothing the spectral sweep is based on the at least one first smoothing filter that takes an average of the power level measurements over time.

4. The method of claim 1 , wherein the first derivative and/or the second derivative are used to identify the matched positive and negative gradients.

5. The method of claim 1 , further comprising sending a notification and/or an alarm to at least one remote device after detecting the at least one signal.

6. A system for automatic signal detection in an environment, comprising:

at least one sensing device for detecting signals in the environment;

wherein the at least one sensing device is operable to sweep and learn the environment, thereby creating learning data including power level measurements of one or more frequency bins within the environment;

wherein the at least one sensing device is operable to form a knowledge map based on the power level measurements of the one or more frequency bins within the environment;

wherein the at least one sensing device is operable to create a profile of the environment based on the knowledge map;

wherein the at least one sensing device is operable to scrub a spectral sweep against the profile;

wherein the at least one sensing device is operable to calculate a first derivative of the power level measurements and a second derivative of the power level measurements;

wherein the at least one sensing device is operable to smooth the spectral sweep with a correction vector and at least one first smoothing filter;

wherein the at least one sensing device is operable to detect at least one signal in the environment based on a machine learning algorithm;

wherein a second smoothing filter is performed only on frequencies outside a frequency range of the at least one signal;

wherein the machine learning algorithm includes signal variance determination from different locations and times;

wherein the at least one sensing device is operable to remove areas identified by matched positive and negative gradients and connect points between removed areas to determine a baseline;

wherein the at least one sensing device is operable to create a reconstructed signal using compressed data for deltas and the baseline;

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

wherein the learning data is based on demodulating and/or decoding the at least one signal;

wherein the at least one sensing device is operable to fill gaps during creation of the reconstructed signal where data of the at least one signal is absent;

wherein the deltas are operable to be used for signal identification, interference identification, neighboring band identification, device identification, and/or signal optimization;

wherein the at least one sensing device is operable to index the power level measurements of the one or more frequency bins based on a learning routine; and

wherein the at least one sensing device is operable to generate signal variance reports, power usage reports, radio frequency (RF) survey reports, and/or signal optimization reports.

7. The system of claim 6 , further comprising a remote device in network-based communication with the at least one sensing device, wherein the knowledge map and/or detecting results are displayed on a remote device in real time.

8. The system of claim 6 , wherein the at least one sensing device is operable to fine-tune a threshold of power level on a segmented basis.

9. The system of claim 6 , wherein smoothing the spectral sweep is based on the at least one first smoothing filter that takes an average of the power level measurements over time.

10. The system of claim 6 , wherein the first derivative and/or the second derivative are used to identify the matched positive and negative gradients.

11. The system of claim 6 , wherein one or more of the at least one sensing device includes a global positioning system (GPS) receiver.

12. The system of claim 6 , wherein the at least one sensing device is operable to obtain a different knowledge map from another sensing device.

13. A system for automatic signal detection and/or interference detection in an environment, comprising:

at least one sensing device for detecting signals in the environment; and

at least one remote device;

wherein the at least one sensing device is operable to sweep and learn the environment, thereby creating learning data including power level measurements of one or more frequency bins within the environment;

wherein the at least one sensing device is operable to form a knowledge map based on the power level measurements of the one or more frequency bins within the environment;

wherein the at least one sensing device is operable to create a profile of the environment based on the knowledge map;

wherein the at least one sensing device is operable to scrub a spectral sweep against the profile;

wherein the at least one sensing device is operable to index the power level measurements for the one or more frequency bins within the electromagnetic environment based on a learning routine;

wherein the at least one sensing device is operable to calculate derivatives of the power level measurements;

wherein the at least one sensing device is operable to smooth the spectral sweep with a correction vector and at least one first smoothing filter;

wherein the at least one sensing device is operable to detect at least one signal in the environment based on a machine learning algorithm;

wherein a second smoothing filter is performed only on frequencies outside a frequency range of the at least one signal;

wherein the machine learning algorithm includes signal variance determination from different locations and times;

wherein the at least one sensing device is operable to average the spectral sweep, remove areas identified by matched positive and negative gradients, and connect points between removed areas to determine a baseline;

wherein the at least one sensing device is operable to create a reconstructed signal using compressed data for deltas and the baseline;

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

wherein the learning data is based on demodulating and/or decoding the at least one signal;

wherein the deltas are operable to be used for signal identification, interference identification, neighboring band identification, device identification, and/or signal optimization;

wherein the at least one sensing device is operable to fill gaps during creation of the reconstructed signal where data of the at least one signal is absent;

wherein the at least one sensing device is operable to subtract the baseline from the spectral sweep to reveal the at least one signal;

wherein the at least one sensing device is operable to send a notification and/or an alarm to the at least one remote device after detecting the at least one signal; and

wherein the at least one sensing device is operable to generate signal variance reports, power usage reports, radio frequency (RF) survey reports, and/or signal optimization reports.

14. The system of claim 13 , wherein the at least one sensing device is operable to fine-tune a threshold of power level on a segmented basis.

15. The system of claim 13 , wherein smoothing the spectral sweep is based on the at least one first smoothing filter that takes an average of the power level measurements over time.

Assignments (2)

Continuity (21)