Abstract: A method and system are disclosed for identifying an emitter or transmitter (e.g., among a plurality of emitters) to a desired degree of accuracy. The method or system may receive a signal in a receiver from a transmitter, wherein the signal propagates from the transmitter to the receiver. The method or system may demodulate the received signal to generate a demodulated signal having a carrier frequency of zero and determine a bispectrum associated with the demodulated signal. The method or system may classify the bispectrum into a classification using a neural network having been trained to a signal emitted by the transmitter. The method or system may determine an accuracy of the classification based on a probability of the classification being greater than a threshold.

Abstract: A method is disclosed to receive a signal, in a receiver from a transmitter (e.g., over a period of time). The signal propagates from the transmitter to the receiver in a direction of propagation. The receiver may move in a direction of motion relative to the transmitter. The signal includes a cyclic feature. The method may determine a change rate of a Doppler shift of the cyclic feature in the received signal. The method may determine, based on the change rate of the Doppler shift of the cyclic feature, an angle between the direction of motion of the receiver and the direction of propagation, the range between the receiver and the transmitter, and/or the locations of the transmitter and/or receiver.