Abstract: The disclosed invention uses computer-implemented algorithms, including machine learning algorithms, to detect radiofrequency (RF) transmissions within a congested RF environment. Some embodiments include a method for sampling an RF environment, mapping the sampled signals onto a spectrogram, extracting signal start times from the spectrogram and loading the start times into a bit array. The method continues by correlating a subset of start times with each other, each subset representing a potential pulsed signal. The subsets are selected for strength of correlation by threshold analysis, and then are subject to sine wave analysis to precisely identify start times within the selected subsets before selecting strongly matched subsets by another threshold analysis. In other embodiments, a system for detecting pulsed RF signals includes a RF receiver, a signal detector, a converter for creating a bit array, a correlator, a first threshold discriminator, a sine wave analyzer, and a second threshold discriminator.

Abstract: Using captured and stored wideband historical radio frequency data bearing information to the source of a signal of interest achieved using as few as two receivers and a plurality of commutating antennas. Wideband IQ data streams are received at two or more receivers and stored for later analysis. A first receiver is coupled to a reference antenna and a second receiver is commutatively coupled to a plurality of commutating antennas. Later, streams of wideband IQ data are retrieved for a select period of time and synchronized. From these streams a signal of interest identified and synchronously sampled over an acquisition interval by each receiver. Phase differences of the signal at each of the plurality commutating antennas is measured enabling a determination of the bearing to the common signal of interest.

Abstract: Data gathered from a continual data source is converted into an image and represented by a rectilinear grid defining a grid of pixels. Each pixel in each axis unit of one axis is examined in parallel using a graphic processor unit (GPU) to determine whether any pixels exceed a predefined threshold. Those pixels that exceed the threshold are identified as positive return pixels. Within each axis unit groups of positive return pixels are identified based on a first axis epsilon. Adjacent groups of positive return pixels are assembled by merging the axis units based on a second axis epsilon. Groups of positive return pixels grouped together according to the first axis epsilon and the second axis epsilon are classified and reported as a signal.

Abstract: Narrow brand IQ signals are obfuscated by embedding the signal in a buffered portion of wideband IQ frequency data. After the data has been received and buffered, the receiving transceiver, using a wideband IQ frequency data key, of a predetermined and shared format, decodes and reconstitute the narrowband IQ signal.

Abstract: The disclosed invention includes methods for linking individual software-defined radios (SDR) into a cohesive network of SDRs capable of recording a sample of radiofrequency (RF) signals emitted in an RF environment. Individual SDRs communicate with an IP network, and host a linking application that executes the recording. A user identifies a lead SDR from among the SDRs, and uses the lead SDR to task participating SDRs with reference to a clock source. Also disclosed is a system of SDRs configured to be linked into a cohesive network of SDRs capable of recording a sample of RF signals emitted in an RF environment. Embodiments of the disclosed invention include co-located and dispersed SDRs. Some embodiments use SDRs organized into a mesh network. Embodiments of the disclosed invention are configured to perform total band monitoring, total band capture, RF environment simulation, interference identification, interference simulation, and distributed quality of service evaluation of wireless networks.

Abstract: The disclosed invention uses computer-implemented algorithms, including machine learning algorithms, to detect radiofrequency (RF) transmissions within a congested RF environment. Some embodiments include a method for sampling an RF environment, mapping the sampled signals onto a spectrogram, extracting signal start times from the spectrogram and loading the start times into a bit array. The method continues by correlating a subset of start times with each other, each subset representing a potential pulsed signal. The subsets are selected for strength of correlation by threshold analysis, and then are subject to sine wave analysis to precisely identify start times within the selected subsets before selecting strongly matched subsets by another threshold analysis. In other embodiments, a system for detecting pulsed RF signals includes a RF receiver, a signal detector, a converter for creating a bit array, a correlator, a first threshold discriminator, a sine wave analyzer, and a second threshold discriminator.

Abstract: Capturing, extracting and storing narrowband IQ data for later processing enables timely and efficient analysis. As wideband capture of RF information includes noise and non-signal elements, the present invention detects, extracts and stores narrowband IQ signals for later assessment. By transforming a high-volume data stream to a collection of smaller narrowband signals with greatly reduced storage and on-board processing requirements the present invention facilitates the capability to analyze signals of interest in an otherwise denied environment.

Abstract: The disclosed invention includes methods for linking individual software-defined radios (SDR) into a cohesive network of SDRs capable of recording a sample of radiofrequency (RF) signals emitted in an RF environment. Individual SDRs communicate with an IP network, and host a linking application that executes the recording. A user identifies a lead SDR from among the SDRs, and uses the lead SDR to task participating SDRs with reference to a clock source. Also disclosed is a system of SDRs configured to be linked into a cohesive network of SDRs capable of recording a sample of RF signals emitted in an RF environment. Embodiments of the disclosed invention include co-located and dispersed SDRs. Some embodiments use SDRs organized into a mesh network. Embodiments of the disclosed invention are configured to perform total band monitoring, total band capture, RF environment simulation, interference identification, interference simulation, and distributed quality of service evaluation of wireless networks.

Abstract: Narrow brand IQ signals are obfuscated by embedding the signal in a buffered portion of wideband IQ frequency data. After the data has been received and buffered, the receiving transceiver, using a wideband IQ frequency data key, of a predetermined and shared format, decodes and reconstitute the narrowband IQ signal.

Abstract: Dynamic and reconfigurable data paths for data stream processing and visualization is hereafter described by way of example. Data analytics on streaming data is conducted upon the identification of data processing needs or requirements. As these needs are recognized data paths are independently formed providing each data processing functionality with access to a common data source As requirements change, as new data processing functionalities are requested or existing functionalities are terminated, a connection manager modifies the existing data path architecture while maintaining data paths for ongoing data processing.

Abstract: The disclosed invention uses artificial intelligence (AI) algorithms for detecting and classifying radiofrequency transmissions to model and simulate an RF environment. AI or machine learning (ML) algorithms further assist in determining optimal modulation, bandwidth and center frequency placement of a transmit signal to either fully and efficiently exploit unused spectrum in the RF environment, or to camouflage the signal to evade detection, and therefore interception while providing enough fidelity to the receiver to remain detectable. Such signal shaping is done while maintaining small SWaP-C footprint for system component hardware.

Abstract: The disclosed invention uses artificial intelligence (AI) algorithms for detecting and classifying radiofrequency (RF) transmissions to assemble a target signal library containing information about one or more target signals according to several criteria. A signal generator develops a mimic signal, designed to emulate a target signal based on information stored in the target signal library. In some embodiments, AI or machine learning (ML) algorithms further assist in refining the mimic signal to more effectively resemble the target signal. Such signal mimicry is done while maintaining small SWaP-C footprint for system component hardware.

Abstract: Using captured and stored wideband historical radio frequency data bearing information to the source of a signal of interest achieved using as few as two receivers and a plurality of commutating antennas. Wideband IQ data streams are received at two or more receivers and stored for later analysis. A first receiver is coupled to a reference antenna and a second receiver is commutatively coupled to a plurality of commutating antennas. Later, streams of wideband IQ data are retrieved for a select period of time and synchronized. From these streams a signal of interest identified and synchronously sampled over an acquisition interval by each receiver. Phase differences of the signal at each of the plurality commutating antennas is measured enabling a determination of the bearing to the common signal of interest.

Abstract: Capturing, extracting and storing narrowband IQ data for later processing enables timely and efficient analysis. As wideband capture of RF information includes noise and non-signal elements, the present invention detects, extracts and stores narrowband IQ signals for later assessment. By transforming a high-volume data stream to a collection of smaller narrowband signals with greatly reduced storage and on-board processing requirements the present invention facilitates the capability to analyze signals of interest in an otherwise denied environment.

Abstract: Data gathered from a continual data source is converted into an image and represented by a rectilinear grid defining a grid of pixels. Each pixel in each axis unit of one axis is examined in parallel using a graphic processor unit (GPU) to determine whether any pixels exceed a predefined threshold. Those pixels that exceed the threshold are identified as positive return pixels. Within each axis unit groups of positive return pixels are identified based on a first axis epsilon. Adjacent groups of positive return pixels are assembled by merging the axis units based on a second axis epsilon. Groups of positive return pixels grouped together according to the first axis epsilon and the second axis epsilon are classified and reported as a signal.

Abstract: An intelligent hierarchal agent structure responds to requests and inquires regarding a data environment by parsing the query to actionable sub-questions and assigning each to a primary agent. Upon examination of available data, the agent assesses whether the sub-question can be resolved or whether additional material is needed. In the later instance the agent seeks aid from subordinate or secondary agents which in turn seek aid of other agents in order to generate information as necessary to resolve to the question presented. Upon resolution of the question the output is placed in a common database which is continually monitored by each agent. Agents are engaged in parallel yet respond according to a hierarchal structure.

Abstract: Detection and classification of patterns in high speed streaming data using algorithmic learning processes creates transferable models. Synchronized local data models are housed in a data model repository and upon receiving one or more data points from a continual source of data a determination is made whether the newly collected data falls within an existing data model. If so, the detection is reported. If not the data is stored in an unknown data detection list. Clusters of the data residing in the unknown data list are formed and from those clusters statistical features extracted. An n-dimensional convex hull is fashioned bounding a region within which the statistical features lie thereby establishing a new class of data. The new class of data is, or can be, thereafter transferred to other existing models such that the receiving model can update its data model repository without performing any data analysis.