Blind Source Separation with L1 Regularized Sparse Autoencoder

Jason A. Dabin, Alexander M. Haimovich, Justin Mauger, Annan Dong

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Blind source separation of co-channel communication signals can be performed by structuring the problem with an over-complete dictionary of the channel and solving for the sparse coefficients, which represent the latent transmitted signals. L_{1} regularized least squares is a common approach to imposing sparsity on the latent signal representation while minimizing the reconstruction error. In this paper we propose an unsupervised learning approach for blind source separation using an L_{1} regularized sparse autoencoder with a softthreshold activation function at the hidden layer that is able to separate and fully recover multiple overlapping binary phase shift keying co-channel signals.

Original languageEnglish (US)
Title of host publication2020 29th Wireless and Optical Communications Conference, WOCC 2020
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9781728161242
DOIs
StatePublished - May 2020
Event29th Wireless and Optical Communications Conference, WOCC 2020 - Newark, United States
Duration: May 1 2020May 2 2020

Publication series

Name2020 29th Wireless and Optical Communications Conference, WOCC 2020

Conference

Conference29th Wireless and Optical Communications Conference, WOCC 2020
Country/TerritoryUnited States
CityNewark
Period5/1/205/2/20

All Science Journal Classification (ASJC) codes

  • Artificial Intelligence
  • Computer Networks and Communications
  • Instrumentation
  • Atomic and Molecular Physics, and Optics

Keywords

  • Autoencoder
  • blind source separation
  • co-channel separation
  • sparse coding
  • sparse recovery
  • sparse representation

Fingerprint

Dive into the research topics of 'Blind Source Separation with L1 Regularized Sparse Autoencoder'. Together they form a unique fingerprint.

Cite this