# US 11,910,209 B2 · Large scale radio frequency signal information processing and analysis system using bin-wise processing > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 11,910,209 B2 - Document ID: US11910209B2 - Status: Granted - Kind: B2 - Application number: 16/885,610 - Filed: 2020-05-28 - Published: 2021-01-21 - Granted: 2024-02-20 - Earliest claimed: 2016-03-08 - Assignees: Aurora Insight Inc. - Applicants: Aurora Insight Inc. - Inventors: Jennifer Alvarez; Benjamin Kempke; Wyatt Tyree; Michael Skaug - Web page: https://patentgrep.com/patent/US11910209B2 ## CPC - H04W 24/02: Arrangements for optimising operational condition - H04W 24/08: Testing, {supervising or monitoring} using real traffic - G06N 3/0464: Convolutional networks [CNN, ConvNet] - G06N 3/09: Supervised learning - G06N 20/00: Machine learning - H04B 17/346: {Noise values (signal-to-interference ratio [SIR] or carrier-to-interference ratio [CIR] H04B17/336)} - H04W 64/003: {locating network equipment} - G06N 3/045: Combinations of networks - G06N 3/08: Learning methods - H04W: WIRELESS COMMUNICATION NETWORKS (broadcast communication H04H; communication systems using wireless links for non-selective communication, e.g. wireless extensions H04M1/72) - G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS - H04B: TRANSMISSION ## Abstract A large-scale radio frequency signal information processing and analysis system that provides advanced signal analysis for telecommunication applications, including band capacity and geographical density determinations and detection, classification, identification, and geolocation of signals across a wide range of frequencies and across broad geographical areas. The system may utilize a range of novel algorithms for bin-wise processing, Rayleigh distribution analysis, telecommunication signal classification, receiver anomaly detection, transmitter density estimation, transmitter detection and location, geolocation analysis, telecommunication activity estimation, telecommunication utilization estimation, frequency utilization estimation, and data interpolation. ## Claims ### Claim 1 A system for classifying telecommunication signals, comprising: a computing device comprising a memory and a processor; and a telecommunication signal classifier, comprising a plurality of programming instructions stored in the memory of, and operating on the processor of, the computing device, wherein the plurality of programming instructions, when operating on the processor, causes the computing device to: receive signal information; process the signal information through an image processing algorithm in the time domain to produce a first compact dataset; transform the signal information into the frequency domain; process the signal information through the image processing algorithm in the frequency domain to produce a second compact dataset; and use the first and second compact datasets to train machine learning algorithms to detect, identify, and classify telecommunication signals, wherein the plurality of programming instructions causing the computing device to use the first and second datasets to train the machine learning algorithms to detect, identify, and classify telecommunication signals comprises the plurality of programming instructions causing the computing device to use the first and second datasets to train the machine learning algorithms to: determine distribution of in-phase and quadrature-phase signals, compare the distribution of the in-phase and quadrature-phase signals over a frequency band of interest against noise distribution, and apply thresholds to isolate signals. ### Claim 2 (depends on 1) The system of claim 1, wherein the plurality of programming instructions, when operating on the processor, further cause the computing device to use the first and second compact datasets to train the machine learning algorithms to refine the thresholds. ### Claim 3 (depends on 1) The system of claim 1, wherein the plurality of programming instructions, when operating on the processor, further cause the computing device to use the first and second compact datasets to train the machine learning algorithms to reduce the frequency band of interest. ### Claim 4 (depends on 1) The system of claim 1, wherein the plurality of programming instructions, when operating on the processor, further cause the computing device to use the first and second compact datasets to train the machine learning algorithms to detect, identify, and classify live data signals. ### Claim 5 (depends on 1) The system of claim 1, wherein the plurality of programming instructions, when operating on the processor, further cause the computing device to provide features specific to a signal type to the machine learning algorithms. ### Claim 6 (depends on 5) The system of claim 5, wherein the features specific to the signal type comprises Long Term Evolution (LTE) synchronization symbol. ### Claim 7 A method for classifying telecommunication signals, comprising: receiving signal information; processing the signal information through an image processing algorithm in the time domain to produce a first compact dataset; transforming the signal information into the frequency domain; processing the signal information through the image processing algorithm in the frequency domain to produce a second compact dataset; and using the first and second compact datasets to train machine learning algorithms to detect, identify, and classify telecommunication signals, wherein using the first and second datasets to train the machine learning algorithms to detect, identify, and classify telecommunication signals comprises using the first and second datasets to train the machine learning algorithms to: determine distribution of in-phase and quadrature-phase signals, compare the distribution of the in-phase and quadrature-phase signals over a frequency band of interest against noise distribution, and apply thresholds to isolate signals. ### Claim 8 (depends on 7) The method of claim 7, further comprising using the first and second compact datasets to train the machine learning algorithms to refine the thresholds. ### Claim 9 (depends on 7) The method of claim 7, further comprising using the first and second compact datasets to train the machine learning algorithms to reduce the frequency band of interest. ### Claim 10 (depends on 7) The method of claim 7, further comprising using the first and second compact datasets to train the machine learning algorithms to detect, identify, and classify live data signals. ### Claim 11 (depends on 7) The method of claim 7, further comprising providing features specific to a signal type to the machine learning algorithms. ### Claim 12 (depends on 11) The method of claim 11, wherein providing the features specific to the signal type to the machine learning algorithms comprises providing Long Term Evolution (LTE) synchronization symbol. ### Claim 13 (depends on 12) The method of claim 12, wherein providing the LTE synchronization symbol comprises providing the LTE synchronization symbol based on any one or combination of the primary or secondary synchronization signals or reference signals from one or more antenna ports, or demodulated information block messages. ### Claim 14 A non-transitory computer-readable medium that stores a set of instructions which when executed perform a method executed by the set of instructions comprising: receiving signal information; processing the signal information through an image processing algorithm in the time domain to produce a first compact dataset; transforming the signal information into the frequency domain; processing the signal information through the image processing algorithm in the frequency domain to produce a second compact dataset; and using the first and second compact datasets to train machine learning algorithms to detect, identify, and classify telecommunication signals, wherein using the first and second datasets to train the machine learning algorithms to detect, identify, and classify telecommunication signals comprises sing the first and second datasets to train the machine learning algorithms to: determine distribution of in-phase and quadrature-phase signals, compare the distribution of the in-phase and quadrature-phase signals over a frequency band of interest against noise distribution, and apply thresholds to isolate signals. ### Claim 15 (depends on 14) The non-transitory computer-readable medium of claim 14, further comprising using the first and second compact datasets to train the machine learning algorithms to refine the thresholds. ### Claim 16 (depends on 14) The non-transitory computer-readable medium of claim 14, further comprising using the first and second compact datasets to train the machine learning algorithms to reduce the frequency band of interest. ### Claim 17 (depends on 14) The non-transitory computer-readable medium of claim 14, further comprising using the first and second compact datasets to train the machine learning algorithms to detect, identify, and classify live data signals. ### Claim 18 (depends on 14) The non-transitory computer-readable medium of claim 14, further comprising providing features specific to a signal type to the machine learning algorithms. ### Claim 19 (depends on 18) The non-transitory computer-readable medium of claim 18, wherein providing the features specific to the signal type to the machine learning algorithms comprises providing Long Term Evolution (LTE) synchronization symbol. ### Claim 20 (depends on 19) The non-transitory computer-readable medium of claim 19, wherein providing the LTE synchronization symbol comprises providing the LTE synchronization symbol based on any one or combination of the primary or secondary synchronization signals or reference signals from one or more antenna ports, or demodulated information block messages.