Decoding communication signals in a non-cooperative environment has always been a challenging task. Even after the estimation of various transmission-related parameters, the unknown received signal still cannot be decoded without the correct classification of the incorporated line coding scheme. In this paper, a robust short-sample feature-based approach is presented which recognizes line coding schemes in a sequential manner by an in-depth examination of linked characteristic features. The proposed approach provides an overall correct classification accuracy higher than 90 percent with an input of just 13 bit-waveforms whereas perfect classification accuracy (100 percent) is achieved with just 30 bit-waveforms of the unknown received signal. A detailed comparison considering noiseless as well as noisy channel environment is also carried out vis-à-vis existing approach based on extensive simulation results. Additionally, the paper bridges the gap between theory and simulations to justify the obtained accuracy results for conventional line codes under consideration. The substantial increase in classification accuracy for a smaller number of input bit-waveforms shall aid effective decoding of the unknown received signal even at the initial stages of reception. In general, it can benefit many practical spectrum surveillance applications, where proactiveness is paramount.
Read full abstract