Blind Deinterleaving of Signals in Time Series with Self-Attention Based Soft Min-Cost Flow Learning

Ogul Can; Yeti Ziya Gürbüz; Berkin Yildirim; A. Aydin Alatan

ICASSP 2021accepted0 citations

Blind Deinterleaving of Signals in Time Series with Self-Attention Based Soft Min-Cost Flow Learning

Ogul Can, Yeti Ziya Gürbüz, Berkin Yildirim, A. Aydin Alatan

Abstract

We propose an end-to-end learning approach to address deinterleaving of patterns in time series, in particular, radar signals. We link signal clustering problem to min-cost flow as an equivalent problem once the proper costs exist. We formulate a bi-level optimization problem involving min-cost flow as a sub-problem to learn such costs from the supervised training data. We then approximate the lower level optimization problem by self-attention based neural networks and provide a trainable framework that clusters the patterns in the input as the distinct flows. We evaluate our method with extensive experiments on a large dataset with several challenging scenarios to show the efficiency.

BibTeX

@inproceedings{icassp2021_blinddeinterleav,
  title = {Blind Deinterleaving of Signals in Time Series with Self-Attention Based Soft Min-Cost Flow Learning},
  author = {Ogul Can and Yeti Ziya Gürbüz and Berkin Yildirim and A. Aydin Alatan},
  booktitle = {ICASSP 2021},
  year = {2021}
}