End-to-end radio traffic sequence recognition with recurrent neural networks

Timothy J. O'Shea; Seth Hitefield; Johnathan Corgan

doi:10.1109/GlobalSIP.2016.7905847

End-to-end radio traffic sequence recognition with recurrent neural networks

Timothy J. O'Shea, Seth Hitefield, Johnathan Corgan

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

33 Scopus citations

Abstract

We investigate sequence machine learning techniques on raw radio signal time-series data. By applying deep recurrent neural networks we learn to discriminate between several application layer traffic types on top of a constant envelope modulation without using an expert demodulation algorithm. We show that complex protocol sequences can be learned and used for both classification and generation tasks using this approach.

Original language	English
Title of host publication	2016 IEEE Global Conference on Signal and Information Processing, GlobalSIP 2016 - Proceedings
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	277-281
Number of pages	5
ISBN (Electronic)	9781509045457
DOIs	https://doi.org/10.1109/GlobalSIP.2016.7905847
State	Published - Apr 19 2017
Externally published	Yes
Event	2016 IEEE Global Conference on Signal and Information Processing, GlobalSIP 2016 - Washington, United States Duration: Dec 7 2016 → Dec 9 2016

Publication series

Name	2016 IEEE Global Conference on Signal and Information Processing, GlobalSIP 2016 - Proceedings

Conference

Conference	2016 IEEE Global Conference on Signal and Information Processing, GlobalSIP 2016
Country/Territory	United States
City	Washington
Period	12/7/16 → 12/9/16

Access to Document

10.1109/GlobalSIP.2016.7905847

Cite this

O'Shea, T. J., Hitefield, S., & Corgan, J. (2017). End-to-end radio traffic sequence recognition with recurrent neural networks. In 2016 IEEE Global Conference on Signal and Information Processing, GlobalSIP 2016 - Proceedings (pp. 277-281). Article 7905847 (2016 IEEE Global Conference on Signal and Information Processing, GlobalSIP 2016 - Proceedings). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/GlobalSIP.2016.7905847

O'Shea, Timothy J. ; Hitefield, Seth ; Corgan, Johnathan. / End-to-end radio traffic sequence recognition with recurrent neural networks. 2016 IEEE Global Conference on Signal and Information Processing, GlobalSIP 2016 - Proceedings. Institute of Electrical and Electronics Engineers Inc., 2017. pp. 277-281 (2016 IEEE Global Conference on Signal and Information Processing, GlobalSIP 2016 - Proceedings).

@inproceedings{b26dbecc9d764176929a0e413b4a3242,

title = "End-to-end radio traffic sequence recognition with recurrent neural networks",

abstract = "We investigate sequence machine learning techniques on raw radio signal time-series data. By applying deep recurrent neural networks we learn to discriminate between several application layer traffic types on top of a constant envelope modulation without using an expert demodulation algorithm. We show that complex protocol sequences can be learned and used for both classification and generation tasks using this approach.",

author = "O'Shea, {Timothy J.} and Seth Hitefield and Johnathan Corgan",

note = "Publisher Copyright: {\textcopyright} 2016 IEEE.; 2016 IEEE Global Conference on Signal and Information Processing, GlobalSIP 2016 ; Conference date: 07-12-2016 Through 09-12-2016",

year = "2017",

month = apr,

day = "19",

doi = "10.1109/GlobalSIP.2016.7905847",

language = "English",

series = "2016 IEEE Global Conference on Signal and Information Processing, GlobalSIP 2016 - Proceedings",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "277--281",

booktitle = "2016 IEEE Global Conference on Signal and Information Processing, GlobalSIP 2016 - Proceedings",

}

O'Shea, TJ, Hitefield, S & Corgan, J 2017, End-to-end radio traffic sequence recognition with recurrent neural networks. in 2016 IEEE Global Conference on Signal and Information Processing, GlobalSIP 2016 - Proceedings., 7905847, 2016 IEEE Global Conference on Signal and Information Processing, GlobalSIP 2016 - Proceedings, Institute of Electrical and Electronics Engineers Inc., pp. 277-281, 2016 IEEE Global Conference on Signal and Information Processing, GlobalSIP 2016, Washington, United States, 12/7/16. https://doi.org/10.1109/GlobalSIP.2016.7905847

End-to-end radio traffic sequence recognition with recurrent neural networks. / O'Shea, Timothy J.; Hitefield, Seth; Corgan, Johnathan.
2016 IEEE Global Conference on Signal and Information Processing, GlobalSIP 2016 - Proceedings. Institute of Electrical and Electronics Engineers Inc., 2017. p. 277-281 7905847 (2016 IEEE Global Conference on Signal and Information Processing, GlobalSIP 2016 - Proceedings).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - End-to-end radio traffic sequence recognition with recurrent neural networks

AU - O'Shea, Timothy J.

AU - Hitefield, Seth

AU - Corgan, Johnathan

PY - 2017/4/19

Y1 - 2017/4/19

N2 - We investigate sequence machine learning techniques on raw radio signal time-series data. By applying deep recurrent neural networks we learn to discriminate between several application layer traffic types on top of a constant envelope modulation without using an expert demodulation algorithm. We show that complex protocol sequences can be learned and used for both classification and generation tasks using this approach.

AB - We investigate sequence machine learning techniques on raw radio signal time-series data. By applying deep recurrent neural networks we learn to discriminate between several application layer traffic types on top of a constant envelope modulation without using an expert demodulation algorithm. We show that complex protocol sequences can be learned and used for both classification and generation tasks using this approach.

UR - http://www.scopus.com/inward/record.url?scp=85019245425&partnerID=8YFLogxK

U2 - 10.1109/GlobalSIP.2016.7905847

DO - 10.1109/GlobalSIP.2016.7905847

M3 - Conference contribution

AN - SCOPUS:85019245425

T3 - 2016 IEEE Global Conference on Signal and Information Processing, GlobalSIP 2016 - Proceedings

SP - 277

EP - 281

BT - 2016 IEEE Global Conference on Signal and Information Processing, GlobalSIP 2016 - Proceedings

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 2016 IEEE Global Conference on Signal and Information Processing, GlobalSIP 2016

Y2 - 7 December 2016 through 9 December 2016

ER -

O'Shea TJ, Hitefield S, Corgan J. End-to-end radio traffic sequence recognition with recurrent neural networks. In 2016 IEEE Global Conference on Signal and Information Processing, GlobalSIP 2016 - Proceedings. Institute of Electrical and Electronics Engineers Inc. 2017. p. 277-281. 7905847. (2016 IEEE Global Conference on Signal and Information Processing, GlobalSIP 2016 - Proceedings). doi: 10.1109/GlobalSIP.2016.7905847

End-to-end radio traffic sequence recognition with recurrent neural networks

Abstract

Publication series

Conference

Access to Document

Other files and links

Fingerprint

Cite this