IP Library Granted Patent US 12,381,639
Granted Patent B2
US 12,381,639 · App. 18/415,847 · Granted Aug 5, 2025

Radio-frequency signal processing systems and methods

Inventors: Alexander Wulff (New York, NY); Benjamin Harpe (New York, NY); Isaac Struhl (New York, NY)
Assignee: Distributed Spectrum Inc.
H04B17/102G01S5/02213H04B7/15H04B17/13H04B17/18H04B17/3911H04B17/3913H04W4/38G06F18/214H04B1/0003H04B17/27H04L27/0002
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 12,381,639
App. No.
18/415,847
Granted
Aug 5, 2025
Kind
B2
Abstract

The present disclosure provides radio-frequency (RF) systems that can detect the presence of RF signals received by the system, as well as determine characteristics such as the operating frequency of RF signals, the type of RF source that transmitted each RF signal, and/or the location of each RF source with high precision and sensitivity while using low cost, scalable electronics that are versatile enough for deployment in a variety of environments. Such systems can employ a network of RF sensors that can coordinate in response to communication with a computer to perform any such detection and/or determination using trained models executed onboard the RF sensors and/or the computer. RF signals may have unique characteristics when received at one or more RF sensors that may be detected using trained models described herein, even in high noise or non-line of sight (LOS) environments and with low cost, low resolution RF receiver hardware.

Claims (129)

1. A radio-frequency (RF) sensor, comprising:

an RF antenna; and

a processor operatively coupled to memory and configured to:

receive RF radiation via the RF antenna;

input, to a trained model, data indicative of characteristics of an RF signal among the RF radiation; and

based on an output from the trained model, determine at least one of:

a frequency of the RF signal;

a modulation type of the RF signal;

a power level of the RF signal;

a time period of reception of the RF signal at the RF sensor;

a signal-to-noise ratio (SNR) of the RF sensor;

an RF signal type of the RF signal;

an association of the RF signal with a type of RF source;

a deviation of the RF signal over time;

a deviation in operating condition of an RF source of the RF signal; and/or

that the RF signal is a new RF signal that is not associated with an operating environment in which the RF sensor received the RF signal,

wherein the processor is configured to, based on the output of the trained model, determine the deviation of the RF signal over time, and the deviation is in power level and/or SNR.

2. The RF sensor of claim 1 , wherein the processor is configured to, based on the output of the trained model, determine at least one of:

the RF signal type of the RF signal;

the association of the RF signal with the type of RF source; and/or

that the RF signal is the new RF signal that is not associated with the operating environment.

3. A radio-frequency (RF) sensor, comprising:

an RF antenna;

a processor operatively coupled to memory and configured to:

receive RF radiation via the RF antenna;

input, to a trained model, data indicative of characteristics of an RF signal among the RF radiation; and

based on an output from the trained model, determine at least one of:

a frequency of the RF signal;

a modulation type of the RF signal;

a power level of the RF signal;

a time period of reception of the RF signal at the RF sensor;

a signal-to-noise ratio (SNR) of the RF sensor;

an RF signal type of the RF signal;

an association of the RF signal with a type of RF source;

a deviation of the RF signal over time;

a deviation in operating condition of an RF source of the RF signal; and/or

that the RF signal is a new RF signal that is not associated with an operating environment in which the RF sensor received the RF signal; and

a software-defined radio (SDR) configured to generate and provide digital samples of the RF radiation to the processor,

wherein the processor is configured to obtain the data indicative of the characteristics of the RF signal using the digital samples.

4. A radio-frequency (RF) sensor, comprising:

an RF antenna; and

a processor operatively coupled to memory and configured to:

receive RF radiation via the RF antenna;

input, to a trained model, data indicative of characteristics of an RF signal among the RF radiation; and

based on an output from the trained model, determine at least one of:

a frequency of the RF signal;

a modulation type of the RF signal;

a power level of the RF signal;

a time period of reception of the RF signal at the RF sensor;

a signal-to-noise ratio (SNR) of the RF sensor;

an RF signal type of the RF signal;

an association of the RF signal with a type of RF source;

a deviation of the RF signal over time;

a deviation in operating condition of an RF source of the RF signal; and/or

that the RF signal is a new RF signal that is not associated with an operating environment in which the RF sensor received the RF signal,

wherein the processor is further configured to, based on the output from the trained model, transmit, over a communication network to a second processor, RF characteristic data indicative of a characteristic of the RF signal.

5. The RF sensor of claim 4 , wherein the RF characteristic data comprises digital samples of the RF radiation that include the RF signal.

6. The RF sensor of claim 1 , wherein the data indicative of the characteristics of the RF signal comprises digital samples of the RF radiation.

7. A radio-frequency (RF) sensor, comprising:

an RF antenna;

a processor operatively coupled to memory and configured to:

receive RF radiation via the RF antenna;

input, to a trained model, data indicative of characteristics of an RF signal among the RF radiation, the trained model comprising a trained statistical classifier (TSC) and/or a trained regression model;

based on an output of the trained model, determine a characteristic of the RF signal and/or of an RF source that transmitted the RF signal; and

a software-defined radio (SDR) configured to generate and provide digital samples of the RF radiation to the processor,

wherein the processor is configured to obtain the data indicative of the characteristics of the RF signal using the digital samples.

8. A radio-frequency (RF) sensor, comprising:

an RF antenna; and

a processor operatively coupled to memory and configured to:

receive RF radiation via the RF antenna;

input, to a trained model, data indicative of characteristics of an RF signal among the RF radiation, the trained model comprising a trained statistical classifier (TSC) and/or a trained regression model; and

based on an output of the trained model, determine a characteristic of the RF signal and/or of an RF source that transmitted the RF signal,

wherein the processor is further configured to, based on the output from the trained model, transmit, over a communication network to a second processor, RF characteristic data indicative of a characteristic of the RF signal.

9. The RF sensor of claim 8 , wherein the RF characteristic data comprises digital samples of the RF radiation that include the RF signal.

10. The RF sensor of claim 7 , wherein the processor is configured to, based on the output of the trained model, determine at least one of:

an RF signal type of the RF signal;

an association of the RF signal with a type of RF source;

a deviation of the RF signal over time; and/or

that the RF signal is a new RF signal that is not associated with an operating environment in which the RF sensor received the RF signal.

11. The RF sensor of claim 7 , wherein the data indicative of the characteristics of the RF signal comprises digital samples of the RF radiation.

12. A radio-frequency (RF) system, comprising:

an RF sensor, comprising:

an RF antenna; and

a first processor operatively coupled to first memory and configured to:

receive RF radiation via the RF antenna;

input, to a trained model, digital samples of an RF signal among the RF radiation; and

based on an output from the trained model, transmit, over a communication network, data indicative of characteristics of the RF signal; and

a second processor operatively coupled to second memory and configured to:

receive, over the communication network, the data indicative of characteristics of the RF signal; and

based on the data indicative of characteristics of the RF signal, determine at least one of:

a frequency of the RF signal;

a modulation type of the RF signal;

a power level of the RF signal;

a time period of reception of the RF signal at the RF sensor;

a signal-to-noise ratio (SNR) of the RF sensor;

an RF signal type of the RF signal;

an association of the RF signal with a type of RF source;

a deviation of the RF signal over time;

a deviation in operating condition of an RF source of the RF signal; and/or

that the RF signal is a new RF signal that is not associated with an operating environment in which the RF sensor received the RF signal,

wherein the second processor is configured to, based on the data indicative of the characteristics of the RF signal, determine the deviation of the RF signal over time, and the deviation is in power level and/or SNR.

13. The RF system of claim 12 , wherein the second processor is configured to, based on the data indicative of the characteristics of the RF signal, determine at least one of:

the RF signal type of the RF signal;

the association of the RF signal with the type of RF source; and/or

that the RF signal is the new RF signal that is not associated with the operating environment.

14. A radio-frequency (RF) system, comprising:

an RF sensor, comprising:

an RF antenna; and

a first processor operatively coupled to first memory and configured to:

receive RF radiation via the RF antenna;

input, to a trained model, digital samples of an RF signal among the RF radiation; and

based on an output from the trained model, transmit, over a communication network, data indicative of characteristics of the RF signal;

a second processor operatively coupled to second memory and configured to:

receive, over the communication network, the data indicative of characteristics of the RF signal; and

based on the data indicative of characteristics of the RF signal, determine at least one of:

a frequency of the RF signal;

a modulation type of the RF signal;

a power level of the RF signal;

a time period of reception of the RF signal at the RF sensor;

a signal-to-noise ratio (SNR) of the RF sensor;

an RF signal type of the RF signal;

an association of the RF signal with a type of RF source;

a deviation of the RF signal over time;

a deviation in operating condition of an RF source of the RF signal; and/or

that the RF signal is a new RF signal that is not associated with an operating environment in which the RF sensor received the RF signal; and

a software-defined radio (SDR) configured to generate and provide the digital samples of the RF radiation to the first processor.

15. The RF system of claim 12 , wherein the data indicative of the characteristics of the RF signal comprises digital samples of the RF radiation.

16. The RF system of claim 12 , wherein the trained model comprises a trained statistical classifier (TSC).

17. The RF system of claim 12 , wherein the trained model comprises a trained regression model.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Jun 4, 2024
From: HARPE, BENJAMIN; STRUHL, ISAAC; WULFF, ALEXANDER
To: DISTRIBUTED SPECTRUM INC.
Reel/Frame 067611/0208 →
Continuity (4)
Continuation 17871225 · Jul 22, 2022
Provisional Application 63232605 · Aug 12, 2021
Provisional Application 63225130 · Jul 23, 2021
Related Publication 20240333403A1 · Oct 3, 2024
References Cited (68)
US 9485266B2 · Baxley et al. · 2016 [cited by applicant]
US 9485267B2 · Baxley et al. · 2016 [cited by applicant]
US 9551781B2 · Baxley et al. · 2017 [cited by applicant]
US 9560060B2 · Baxley et al. · 2017 [cited by applicant]
US 9591013B2 · Baxley et al. · 2017 [cited by applicant]
US 9635044B2 · Baxley et al. · 2017 [cited by applicant]
US 9736175B2 · Baxley et al. · 2017 [cited by applicant]
US 9739868B2 · Baxley et al. · 2017 [cited by applicant]
US 9880256B2 · Baxley et al. · 2018 [cited by applicant]
US 9945928B2 · Baxley et al. · 2018 [cited by applicant]
US 10104098B2 · Baxley et al. · 2018 [cited by applicant]
US 10122736B2 · Baxley et al. · 2018 [cited by applicant]
US 10338191B2 · Baxley et al. · 2019 [cited by applicant]
US 10473749B1 · Baxley et al. · 2019 [cited by applicant]
US 10578730B2 · Cardno et al. · 2020 [cited by applicant]
US 11259197B2 · Dzierwa et al. · 2022 [cited by applicant]
US 11916605B2 · Wulff et al. · 2024 [cited by applicant]
US 20160127907A1 · Baxley et al. · 2016 [cited by applicant]
US 20160127931A1 · Baxley et al. · 2016 [cited by applicant]
US 20170238304A1 · Ling et al. · 2017 [cited by applicant]
US 20170261615A1 · Ying et al. · 2017 [cited by applicant]
US 20180324595A1 · Shima · 2018 [cited by applicant]
US 20200007249A1 · Derr et al. · 2020 [cited by applicant]
US 20200143279A1 · West et al. · 2020 [cited by applicant]
US 20200252412A1 · Prasad Koppisetti et al. · 2020 [cited by applicant]
US 20220070822A1 · Behboodi et al. · 2022 [cited by applicant]
US 20220386249A1 · Meshkati et al. · 2022 [cited by applicant]
US 20220399946A1 · Marshall · 2022 [cited by applicant]
US 20230021777A1 · Wulff et al. · 2023 [cited by applicant]
US 20230027893A1 · Wulff et al. · 2023 [cited by applicant]
US 20240248466A1 · Raman · 2024 [cited by examiner]
EP 3910822A1 · 2021 [cited by applicant]
International Search Report and Written Opinion mailed Oct. 6, 2022, in connection with International Application No. PCT/US2022/038012. [cited by applicant]
International Preliminary Report on Patentability dated Feb. 1, 2024, in connection with International Application No. PCT/US2022/038012. [cited by applicant]
[No Author Listed], Fireside Hacks: A Conversation with Distributed Spectrum | NSIN Track. YouTube. Oct. 19, 2021. https://www.youtube.com/watch?v=CquBWk4Jq4E [Last Accessed Aug. 17, 2020]. 3 pages. [cited by applicant]
[No Author Listed], Modular, Real-Time RF Spectrum. Distributed Spectrum. 2021. 9 pages. [cited by applicant]
[No Author Listed], Modular and Highly-Scalable Spectrum. Distributed Spectrum, LLC. 2021. 1 page. [cited by applicant]
[No Author Listed], OmniSIG Sensor and the DeepWave AIR-T. DeepSig Blog. Apr. 13, 2021. 4 pages. https://www.deepsig.ai/news/omnisig-sensor-and-the-deepwave-air-t (Last accessed Aug. 7, 2023). [cited by applicant]
[No Author Listed], Report ITU-R SM.2355-1. SM Series Spectrum Management. 2019. 34 pages. [cited by applicant]
[No Author Listed], Radio Frequency Detection, Spectrum Analysis, and Direction Finding Equipment. Market Survey Report. NUSTL. Apr. 2019. 22 pages. [cited by applicant]
[No Author Listed], RTL-SDR Blog V3 Datasheet. https://www.rtl-sdr.com [Last Accessed Aug. 17, 2022] 8 pages. [cited by applicant]
[No Author Listed], TDOA Transmitter Localization with RTL-SDRs. Panoradio SDR. Jun. 8, 2022. 14 pages. [cited by applicant]
Aksu et al. Requirements for Spectrum Monitoring in Industrial Environments. NISTIR 8195. Nov. 2017. 24 pages. [cited by applicant]
Bhattacharya et al., Selection of Sensors for Efficient Transmitter Location. IEEE Infocom. 2020:2410-2419. [cited by applicant]
Cheng et al., An Algorithm for Jammer Localization in Wireless Sensor Networks. IEEE 26th International Conference on Advanced Information Networking and Applications. 2012:724-731. [cited by applicant]
Ezzati et. al. Distributed Spectrum Sensing Using Radio Environment Maps in Cognitive Radio Networks. Wireless Pers Communication. 2018;101:2241-2254. [cited by applicant]
Figueiredo et al., Low Cost SDR Solution for Spectrum Sensing. ResearchGate. Jul. 2015. 6 pages. [cited by applicant]
Hanna et al., Deep Learning Based Transmitter Identification using Power Amplifier Nonlinearity. arXiv:. Nov. 12, 2018; 1811.04521(1):7 pages. [cited by applicant]
Harp et al., Machine Vision and Deep Learning for Deep Learning for Classification of Radio SETI Signals. arXiv: Feb. 6, 2019;1902.02426: 31 pages. [cited by applicant]
Haykin et al., Cognitive Radio: Brain-empowered wireless communications. IEEE Journal on Selected Areas in Comm. Feb. 2005;23(2):201-220. [cited by applicant]
Kumar et al., LTE Radio Analytics Made Easy and Accessible. SIGCOMM. Aug. 17-22, 2014. 12 pages. [cited by applicant]
Li et al., A Deep Convolutional Network for Multi-Type Signal Detection in Spectrogram. Preprints. May 12, 2020. 13 pages. [cited by applicant]
Li et al., Scaling Deep Learning Models for Spectrum Anomaly Detection. ACM.Jul. 2-5, 2019. 10 pages. [cited by applicant]
Morin et al., Deep Learning-based Transmitter identification on the physical layer. 2020. 23 pages. [cited by applicant]
Mosiane et al., Radio Frequency Interference Detection Using Machine Learning. IEEE Radio and Antenna Days of the Indian Ocean. IOP Conf. Series: Materials Science and Engineering. 2017;198(012012):5 pages. [cited by applicant]
Nika et al., Empirical Validation of Commodity Spectrum Monitoring. SenSys. Nov. 14-16, 2016. 12 pages. [cited by applicant]
O'Shea et. al., Practical Signal Detection and Classification in GNU Radio. Proceedings of the SDR 07. Technical Conference and Product Exposition. 2007. 6 pages. [cited by applicant]
O'Shea et al., Over the Air Deep Learning Based Radio Signal Classification. arXiv:1712.04578v1. 13 pages. [cited by applicant]
Pfammatter et al., A Software-defined Sensor Architecture for Large-scale Wideband Spectrum Monitoring. IPSN. Apr. 14-16, 2015. 12 pages. [cited by applicant]
Robertson et al., Distributed Transmitter Localization by Power Difference of Arrival (PDOA) on a Network of GNU Radio Sensors. Naval Research Laboratory. Feb. 3, 2015:16 pages. [cited by applicant]
Schmitz et al., Demonstration Abstract: Real-time Indoor Localization with TDOA and Distributed Software Defined Radio. IEEE. 2016. 2 pages. [cited by applicant]
Yiwere et al., Sound Source Distance Estimation Using Deep Learning: An Image Classification Approach. Sensors. 2020;20(172):19 pages. [cited by applicant]
Zha et al., A Deep Learning Framework for Signal Detection and Modulation Classification. Sensors. 2019; 19(4042): 21 pages. [cited by applicant]
Zubow et al., DeepTxFinder: Multiple Transmitter Localization by Deep Learning in Crowdsourced Spectrum Sensing. 2020 29th International Conference on Computer Communications and Networks (ICCCN). 2020:1-8. [cited by applicant]
Hall et al., Reference Datasets for Training and Evaluating RF Signal Detection and Classification Models. IEEE. 2019. 5 Pages. [cited by applicant]
Extended European Search Report dated May 16, 2025, in connection with European Application No. 22846670.2. [cited by applicant]
Ponnaluru et al. A software-defined radio testbed for deep learning-based automatic modulation classification. Int J. Commun Syst. Jul. 11, 2020;33:e4556:1-15. DOI:10.1002/dac.4556. [cited by applicant]
Wong et al. The RFML Ecosystem: A Look at the Unique Challenges of Applying Deep Learning to Radio Frequency Applications. arxiv.org. Oct. 1, 2020. 19 pages. [cited by applicant]