Machine Learning with Applications to Autonomous Systems

Citation data:

Mathematical Problems in Engineering, ISSN: 1563-5147, Vol: 2015, Page: 1-2

Publication Year:
Usage 350
Downloads 302
Abstract Views 48
Captures 8
Readers 8
Citations 1
Citation Indexes 1
Repository URL:;;;
Xu, Xin; He, Haibo; Zhao, Dongbin; Sun, Shiliang; Busoniu, Lucian; Yang, Simon X.
Hindawi Limited; DigitalCommons@URI; Mathematical Problems in Engineering
Mathematics; Engineering
article description
Many acoustic channels suffer from interference which is neither narrowband nor impulsive. This relatively long duration partial band interference can be particularly detrimental to system performance. In operational networks, many “dropped” messages are lost due to partial band interference which corrupts different portions of the received signal depending on the relative position of the interferers, information source and receivers due to the slow speed of propagation. We survey recent work in interference mitigation as background motivation to develop a spatial diversity receiver for use in underwater networks and compare this multi-receiver interference mitigation strategy with a recently developed single receiver interference mitigation algorithm using experimental data collected from the underwater acoustic network at the Atlantic Underwater Test and Evaluation Center. The results indicate that both mitigation strategies are effective: parameterized interference cancellation is most effective at moderate SIRs whereas spatial diversity reconstruction is effective and realizes the most gain at high SIRs. We also apply the parametized interference cancellation to the problem of estimating mutually interfering waveforms when it is desired to know both time domain signals and find that it effectively extracts both mutually interfering linear frequency modulated (LFM) and orthogonal frequency division multiplexing (OFDM) waveforms.