Arbitrarily Accurate Classification Applied to Specific Emitter Identification
This addresses the problem of reliable emitter identification for signal processing applications, but it is incremental as it builds on existing deep learning methods.
The authors tackled the problem of achieving arbitrarily high classification accuracy by evaluating subsamples until a desired accuracy level is reached, applied to specific emitter identification on a dataset of 16 radios, resulting in a logarithmic reduction in error rate with linear sample increase, where each addition of eight samples decreases error by one order of magnitude.
This article introduces a method of evaluating subsamples until any prescribed level of classification accuracy is attained, thus obtaining arbitrary accuracy. A logarithmic reduction in error rate is obtained with a linear increase in sample count. The technique is applied to specific emitter identification on a published dataset of physically recorded over-the-air signals from 16 ostensibly identical high-performance radios. The technique uses a multi-channel deep learning convolutional neural network acting on the bispectra of I/Q signal subsamples each consisting of 56 parts per million (ppm) of the original signal duration. High levels of accuracy are obtained with minimal computation time: in this application, each addition of eight samples decreases error by one order of magnitude.