Abstract: A system and method for managing node status in a MANET includes each node identifying node status data and clusterhead priority value data in data packets. Clusterhead priority values define which node dominates in the event of a clusterhead collision. Clusterhead priority values prevent clusterhead switching based solely on first to declare. Each node may define a specific set of redundancy factors when determining if the node should be characterized as a gateway node. The specific set of redundancy factors is based on node capabilities to promote stability in gateway selection.

Abstract: A computerized neural network training and testing environment trains and validates a neural network to produce outputs corresponding to a digital signal processing (DSP) algorithm. After validation and testing, the neural network is replicable in any processing environment, independent of device architecture. Such devices may also include a neural network having a reversed process flow to produce a digital signal corresponding to an inverse of the DSP algorithm.

Abstract: A system and method for detecting, localizing, and classifying RF signals via probability analysis in the decision space include receiving a wideband IQ sample stream and performing a probability analysis to isolate noise from the magnitude spectrum. Derived probability information is used for RF detection and localization. The probability analysis is a Bayesian probability analysis and the detection and localization algorithm is a modified “you only look once” (YOLO) algorithm.

Abstract: A computing device is disclosed, in accordance with one or more embodiments of the present disclosure. A computing device may include operational processors, configured to execute a set of program instructions, wherein the set of program instructions is configured to cause the operational processors to: receive input signals indicative of input conditions; determine input conditions based input signals; determine output signals based on the determined input conditions; and provide determined output signals. The computing device may further include machine-learning processors, wherein the machine-learning processors are configured to develop machine-learning analyzers, wherein the machine-learning analyzers are configured to: identify operational parameters of the operational processors; determine modifications to the set of program instructions, wherein the modifications satisfy a selected quality metric; and provide the modifications to the operational processors.

Abstract: In embodiments, a communication node of a multi-node communication network includes a controller communicatively coupled to a communication interface, wherein the controller is configured to: acquire a data payload to be transmitted based on a randomized transmission interval; duplicate a bit sequence of the data payload with a selected spreading pattern; perform bit-to-symbol mapping of the bit sequence based on a selected M-ary number to generate a data payload symbol sequence; randomize a location or value of one or more pilot symbols and one or more data carriers of the data payload symbol sequence; transform frequency-domain symbols of the data payload symbol sequence into time-domain symbols to generate a time-domain data payload signal; remove amplitude fluctuation of the data payload signal to generate a phasor data payload signal; and transmit the phasor data payload signal to at least one additional communication node of the multi-node communication network.

Abstract: A spectral harvesting system has one or more sensor modules and a processor. The sensor modules autonomously scan RF signals over a range of frequencies in a region of interest. The processor receives observed RF signals from the sensor modules, and performs signal analysis on the observed RF signals received. The signal analysis includes converting the observed RF signals into a frequency signal in a frequency domain, temporally averaging the frequency signal to provide a temporally averaged frequency signal, performing a coarse estimate of the spectral noise floor of the observed RF signals based on the temporally averaged frequency signal using an opening technique that performs an erosion process followed by a dilation process on the temporally averaged frequency signal, and determining an a-posteriori signal presence probability of a signal being present from an RF emitter in the region of interest based on the coarse estimate.

Abstract: An apparatus is shown for detecting speech in an audio signal obtained from an input device, the audio including speech and noise. The apparatus includes a processing circuit which includes a filter configured to smooth the audio signal. The processing circuit is configured to control the bandwidth of the filter based on characteristics of the audio signal and to provide a smoothed signal obtained from the filter to a voice activity detector configured to determine whether the smoothed signal represents speech.

Abstract: A method for detecting carrier wave dropout may include but is not limited to: a) receiving a carrier wave; b) determining a carrier wave power; c) applying a Kalman filter to the carrier wave power; d) detecting a decrease in carrier wave power; and e) delaying a transmission of the carrier wave to a demodulator. A system for detecting carrier wave dropout may include, but is not limited to: a) circuitry for receiving a carrier wave; b) circuitry for determining a carrier wave power; c) circuitry for applying a Kalman filter to the carrier wave power; d) circuitry for detecting a decrease in carrier wave power; and e) circuitry for delaying a transmission of the carrier wave to a demodulator.

Abstract: The present invention is directed to a method and a system for detecting carrier dropout. A method for detecting carrier wave dropout in accordance with the present invention may comprise one or more of the following steps: a) receiving a carrier wave; b) applying a Kalman filter to the carrier wave; c) detecting a decrease in carrier wave power; d) delaying a transmission of the carrier wave to a demodulator. A system for detecting carrier wave dropout may comprise one or more of: a) circuitry for receiving a carrier wave; b) circuitry for applying a Kalman filter to the carrier wave; c) circuitry for detecting a decrease in carrier wave power; d) circuitry for delaying a transmission of the carrier wave to a demodulator.