Self-supervised Anomaly Detection for Narrowband SETI
The Search for Extra-terrestrial Intelligence (SETI) aims to find technological signals of extra-solar origin. Radio frequency SETI is characterized by large unlabeled datasets and complex interference environment.
The infinite possibilities of potential signal types require generalizable signal processing techniques with little human supervision. We present a generative model of self-supervised deep learning that can be used for anomaly detection and spatial filtering. We develop and evaluate our approach on spectrograms containing narrowband signals collected by Breakthrough Listen at the Green Bank telescope. The proposed approach is not meant to replace current narrowband searches but to demonstrate the potential to generalize to other signal types.
Yunfan Gerry Zhang, Ki Hyun Won, Seung Woo Son, Andrew Siemion, Steve Croft
(Submitted on 15 Jan 2019)
Comments: 5 pages, 3 figures
Subjects: Instrumentation and Methods for Astrophysics (astro-ph.IM)
Journal reference: IEEE GlobalSIP 2018
Cite as: arXiv:1901.04636 [astro-ph.IM] (or arXiv:1901.04636v1 [astro-ph.IM] for this version)
Submission history
From: Yunfan Zhang G.
[v1] Tue, 15 Jan 2019 01:59:30 UTC (1,658 KB)
https://arxiv.org/abs/1901.04636
Astrobiology