Abstract: A closed loop, real-time, cognitive Electronic Warfare (EW) system without a threat database includes an EW receiver for receiving radar threat signals; a Signal Analysis and Characterization module; a Pulse to Emitter Association sub-module; a Function De-interleaving Classifier sub-module; a Threat Behavior Model sub-module; a Countermeasures Synthesis module; a Capability, Severity, and Intent sub-module; a Countermeasure Selection sub-module; a Countermeasure Optimization sub-module; a Countermeasures Effectiveness Assessment module; a Resource Management module; and an EW transmitter.

Abstract: A method of selecting and optimizing a countermeasure for application against a novel, ambiguous, or unresponsive radar threat includes selecting a candidate countermeasure and an initial parameter set and varying at least one of the parameters while the effectiveness of the candidate countermeasure against the radar threat is assessed, for example by a human observer. Embodiments include repeating the process with additional candidate countermeasures. For an unresponsive radar threat, a previously effective countermeasure can be selected as the candidate countermeasure. For an ambiguous radar threat, at least one countermeasure previously verified as effective against a partially matching known threat can be selected as the candidate countermeasure. Correlated parameters can be simultaneously varied.

Abstract: A Deep-Learning (DL) system for representation and construction or reconstruction of signals includes an encoder stage; an encoding; an optional modification stage; a decoder stage, and a (re)construction stage. The encoder stage includes layers of dilated convolutions, and the encoder maps from an input representation into a latent embedded representation. It learns a set of features that encode the input signals. The encoding stage comprises latent space; the decoder stage maps from latent features back to an output of the same size as the input signals, whereby the output has the same dimensionality and representation as the input signals. Modification to the signal can be conducted within the latent representation to alter the (re)construction for specific tasks, such as increasing a device's RF fingerprint.

Abstract: A system whereby individual RF emitter devices are distinguished in real-world environments through deep-learning comprising an RF receiver for receiving RF signals from a plurality of individual devices; a preprocessor configured to produce complex-valued In-phase (I) and Quadrature (Q) IQ signal sample representations; a two-stage Augmented Dilated Causal Convolution (ADCC) network comprising a stack of dilated causal convolution layers and traditional convolutional layers configured to process I and Q components of the complex IQ samples; transfer learning comprising a classifier and a cluster embedding dense layer; unsupervised clustering whereby the RF signals are grouped according to a device that transmitted the RF signal; and an output identifying the individual RF emitter device whereby the individual RF emitter device is distinguished in the real-world environment.

Abstract: A Deep-Learning (DL) explainable AI system for Radio Frequency (RF) machine learning applications with expert driven neural explainability of input signals combines three algorithms (A1, A2, and A3). A1 is a neural network that learns to classify spectrograms. During training, A1 learns to map a spectrogram to its paired label. It outputs a label estimate from a spectrogram. Labels account for device number and spectrum utilization. The neural network is built on two-dimensional dilated causal convolutions to account for frequency and time dimensions of spectrogram data. A2 is a user-defined function that converts an input spectrogram into a vector that quantifies human-identifiable elements of the spectrogram. A3 is a random forest feature extraction algorithm. It takes as input the outputs of A2 and A1. From these, A3 learns which elements in the vector output by A2 were most important for choosing the labels output from A1.

Abstract: A system whereby individual RF emitter devices are distinguished in real-world environments through deep-learning comprising an RF receiver for receiving RF signals from a plurality of individual devices; a preprocessor configured to produce complex-valued In-phase (I) and Quadrature (Q) IQ signal sample representations; a two-stage Augmented Dilated Causal Convolution (ADCC) network comprising a stack of dilated causal convolution layers and traditional convolutional layers configured to process I and Q components of the complex IQ samples; transfer learning comprising a classifier and a cluster embedding dense layer; unsupervised clustering whereby the RF signals are grouped according to a device that transmitted the RF signal; and an output identifying the individual RF emitter device whereby the individual RF emitter device is distinguished in the real-world environment.

Abstract: The discriminability of an RF fingerprint is increased by “abstracting,” “enhancing,” and “reconstructing” a digital signal before it is transmitted, where the abstraction is a reversible nonlinear compression, the enhancement is a modification of the abstracted data, and the reconstruction is a mapping-back of the abstraction. During a training phase, for each individual RF transmitter, RF fingerprints are analyzed and candidate enhancements are modified until a successful enhancement is identified that provides satisfactory discriminability improvement with minimal signal degradation. The successful enhancement is implemented in the RF transmitter, and the RF fingerprint is communicated to receivers for subsequent detection and verification. Reinforcement learning can direct modifications to the candidate enhancements. The abstraction can implement a deep generative model such as an auto-encoder.

Abstract: A method of selecting and optimizing a countermeasure for application against a novel, ambiguous, or unresponsive radar threat includes selecting a candidate countermeasure and an initial parameter set and varying at least one of the parameters while the effectiveness of the candidate countermeasure against the radar threat is assessed, for example by a human observer. Embodiments include repeating the process with additional candidate countermeasures. For an unresponsive radar threat, a previously effective countermeasure can be selected as the candidate countermeasure. For an ambiguous radar threat, at least one countermeasure previously verified as effective against a partially matching known threat can be selected as the candidate countermeasure. Correlated parameters can be simultaneously varied.

Abstract: A method of assessing the effectiveness of an electronic countermeasure (ECM) applied against an unknown, ambiguous, or unresponsive radar threat includes monitoring changes in a radar-associated factor while applying the ECM and determining if the ECM is disrupting the hostile radar. The radar-associated factor can be a weapon that is controlled by the radar threat, and assessing the ECM can include determining whether the weapon is misdirected due to applying the ECM. Or the radar-associated factor can be a feature of an RF waveform emitted by the radar threat, and assessing the ECM can include determining if the feature is changed due to applying the ECM. Continuous changes in the feature can indicate unsuccessful attempts to mitigate the ECM. Return of the feature to a pre-threat state can indicate disruption of the radar. The ECM can be selected from a library of countermeasures pre-verified as effective against known threats.

Abstract: A closed loop, real-time, cognitive Electronic Warfare (EW) system without a threat database includes an EW receiver for receiving radar threat signals; a Signal Analysis and Characterization module; a Pulse to Emitter Association sub-module; a Function De-interleaving Classifier sub-module; a Threat Behavior Model sub-module; a Countermeasures Synthesis module; a Capability, Severity, and Intent sub-module; a Countermeasure Selection sub-module; a Countermeasure Optimization sub-module; a Countermeasures Effectiveness Assessment module; a Resource Management module; and an EW transmitter.

Abstract: One or more defined countermeasures are selected from a countermeasure library, populated with parameters, and applied against an unknown, ambiguous, or unresponsive imminent radar threat based on an analysis of a hostile RF waveform emitted by the radar threat. The analysis can include comparing static and/or dynamic features of the hostile RF waveform with features of known hostile RF waveforms. A parameter set associated with the selected defined countermeasure in the countermeasure library can be selected. Waveform features can be categorized and sub-categorized for comparison with the known hostile waveforms. A plurality of features can be detected and compared. The analysis can include correlating behavior patterns of a plurality of hostile RF waveforms emitted by the radar threat. A cognitive intelligence trained using a threat database and library of corresponding countermeasures can analyze the hostile RF waveform, select the defined countermeasure, and/or select or generate the parameters.

Abstract: An artifact-suppressing neural network (NN) kernel comprising at least one neural network, implemented in replacement of a DSP, provides comparable or better performance under non-edge conditions, and superior performance under edge conditions, due to the ease of updating the NN kernel training without enlarging its computational footprint or latency to address a new edge condition. In embodiments, the NN kernel can be implemented in a field programmable gate array (FPGA) or application specific integrated circuit (ASIC), which can be configured as a direct DSP replacement. In various embodiments, the NN kernel training can be updated in near real time when a new edge condition is encountered in the field. The NN kernel can include DCC lower layers and dense upper layers. Initial NN kernel training can require fewer examples. Example embodiments include a noise suppression NN kernel and a modem NN kernel.

Abstract: The discriminability of an RF fingerprint is increased by “abstracting,” “enhancing,” and “reconstructing” a digital signal before it is transmitted, where the abstraction is a reversible nonlinear compression, the enhancement is a modification of the abstracted data, and the reconstruction is a mapping-back of the abstraction. During a training phase, for each individual RF transmitter, RF fingerprints are analyzed and candidate enhancements are modified until a successful enhancement is identified that provides satisfactory discriminability improvement with minimal signal degradation. The successful enhancement is implemented in the RF transmitter, and the RF fingerprint is communicated to receivers for subsequent detection and verification. Reinforcement learning can direct modifications to the candidate enhancements. The abstraction can implement a deep generative model such as an auto-encoder.

Abstract: A method for predicting subject trustworthiness includes using at least one classifier to predict truthfulness of subject responses to prompts during a local or remote interview, based on subject responses and response times, as well as interviewer impressions and response times, and, in embodiments, also biometric measurements of the interviewer. Data from the subject interview is normalized and analyzed relative to an experience database previously created using data obtained from test subjects. Classifier prediction algorithms incorporate assumptions that subject response times are indicators of truthfulness, that subjects will tend to be consistently truthful or deceitful, and that conscious and subconscious impressions of the interviewer are predictive of subject trustworthiness. Data regarding interviewer impressions can be derived from interviewer response times, interviewer questionnaire answers, and/or interviewer biometric data.

Abstract: A method of detecting electromagnetic signal sources of interest includes applying reinforcement learning to automatically and continuously update a receiver scan schedule wherein an agent is reinforced according to comparisons between expected and actual degrees of success after each schedule update, actual degrees of success being estimated by applying to signal data a plurality of value scales applicable to a plurality of reward classes. An exponential scale can be applied across the plurality of reward classes. A companion system can provide data analysis to the agent. The agent can include an actor module that determines schedule updates and a critic module that determines the degrees of scanning success and awards the reinforcements. Embodiments implement a plurality of agents according to asynchronous multiple-worker actor/critic reinforcement learning.

Abstract: A method for predicting subject trustworthiness includes using at least one classifier to predict truthfulness of subject responses to prompts during a local or remote interview, based on subject responses and response times, as well as interviewer impressions and response times, and, in embodiments, also biometric measurements of the interviewer. Data from the subject interview is normalized and analyzed relative to an experience database previously created using data obtained from test subjects. Classifier prediction algorithms incorporate assumptions that subject response times are indicators of truthfulness, that subjects will tend to be consistently truthful or deceitful, and that conscious and subconscious impressions of the interviewer are predictive of subject trustworthiness. Data regarding interviewer impressions can be derived from interviewer response times, interviewer questionnaire answers, and/or interviewer biometric data.

Abstract: A system and method for platform independent LOS visual information transmission is disclosed. A transmitter consists of a series of sequential images that are stacked together to form frames in a video transmission. Each image is modulated spatially, by color, and by intensity. The data is transmitted over an LOS visual channel. The receiver first captures each individual image from the received video, and then demodulates each image in the three areas it was modulated spatially, by color, and by intensity. LOS visual information transmission allows for secure data transfer and reduces interference from other applications.

Abstract: A system and method for platform independent LOS visual information transmission is disclosed. A transmitter consists of a series of sequential images that are stacked together to form frames in a video transmission. Each image is modulated spatially, by color, and by intensity. The data is transmitted over an LOS visual channel. The receiver first captures each individual image from the received video, and then demodulates each image in the three areas it was modulated spatially, by color, and by intensity. LOS visual information transmission allows for secure data transfer and reduces interference from other applications.