On Channel Classification by Using DTMB Signal

Jin, M; Xiong, J; Liu, B; Xiao, L

On Channel Classification by Using DTMB Signal

Jin, M Xiong, J Liu, B

Xiao, L

Permalink

Publisher:: IEEE
Publication Type:: Conference Proceeding
Citation:: 2020 IEEE International Symposium on Broadband Multimedia Systems and Broadcasting (BMSB), 2021, 2020-October
Issue Date:: 2021-03-19

Closed Access

	Filename	Description	Size
	On_Channel_Classification_by_Using_DTMB_Signal.pdf	Published version	221.96 kB	Adobe PDF	View/Open

Copyright Clearance Process

Recently Added
In Progress
Closed Access

This item is closed access and not available.

Full metadata record

Field	Value	Language
dc.contributor.author	Jin, M
dc.contributor.author	Xiong, J
dc.contributor.author	Liu, B https://orcid.org/0000-0002-3603-6617
dc.contributor.author	Xiao, L
dc.date	2020-10-27
dc.date.accessioned	2022-06-13T00:40:38Z
dc.date.available	2022-06-13T00:40:38Z
dc.date.issued	2021-03-19
dc.identifier.citation	2020 IEEE International Symposium on Broadband Multimedia Systems and Broadcasting (BMSB), 2021, 2020-October
dc.identifier.isbn	978-1-7281-5784-9
dc.identifier.issn	2155-5044
dc.identifier.issn	2155-5052
dc.identifier.uri	http://hdl.handle.net/10453/158132
dc.description.abstract	This paper proposes machine learning algorithms to classify channels by using Digital Terrestrial Multimedia Broadcast (DTMB) signal. Channel state information (CSI) usually reflects the environment where a receiver is in. In this paper, the DTMB signal is adopted to extract the CSI features, including cross-correlation of the PN sequence in frame header and the baseband DTMB signal and the high order cumulants (HOCs) of the DTMB signal. Machine Learning algorithms, K-nearest neighbor (KNN), supported vector machine (SVM), Random Forest and Neural Network with one hidden layer, are employed respectively to classify and recognize ten typical broadcasting channel models. Simulations illustrate that the accuracy of the scheme based on the PN correlation features outweighs the HOCs features; and the adopted classification algorithms all show good performance in terms of accuracy; moreover, KNN has the lowest complexity compared to the other three. The accuracy of KNN based on PN correlation is over 95% even when the SNR is below -5dB if the correlation gains of two neighbour frame headers are combined.
dc.language	en
dc.publisher	IEEE
dc.relation.ispartof	2020 IEEE International Symposium on Broadband Multimedia Systems and Broadcasting (BMSB)
dc.relation.ispartof	IEEE International Symposium on Broadband Multimedia Systems and Broadcasting
dc.relation.ispartofseries	IEEE International Symposium on Broadband Multimedia Systems and Broadcasting
dc.relation.isbasedon	10.1109/bmsb49480.2020.9379455
dc.rights	info:eu-repo/semantics/closedAccess
dc.title	On Channel Classification by Using DTMB Signal
dc.type	Conference Proceeding
utslib.citation.volume	2020-October
utslib.location.activity	Paris, France
pubs.organisational-group	/University of Technology Sydney
pubs.organisational-group	/University of Technology Sydney/Faculty of Engineering and Information Technology
pubs.organisational-group	/University of Technology Sydney/Faculty of Engineering and Information Technology/School of Computer Science
utslib.copyright.status	closed_access	*
pubs.consider-herdc	false
dc.date.updated	2022-06-13T00:40:37Z
pubs.finish-date	2020-10-29
pubs.place-of-publication	Piscataway, USA
pubs.publication-status	Published
pubs.start-date	2020-10-27
pubs.volume	2020-October
dc.location	Piscataway, USA

Abstract:

This paper proposes machine learning algorithms to classify channels by using Digital Terrestrial Multimedia Broadcast (DTMB) signal. Channel state information (CSI) usually reflects the environment where a receiver is in. In this paper, the DTMB signal is adopted to extract the CSI features, including cross-correlation of the PN sequence in frame header and the baseband DTMB signal and the high order cumulants (HOCs) of the DTMB signal. Machine Learning algorithms, K-nearest neighbor (KNN), supported vector machine (SVM), Random Forest and Neural Network with one hidden layer, are employed respectively to classify and recognize ten typical broadcasting channel models. Simulations illustrate that the accuracy of the scheme based on the PN correlation features outweighs the HOCs features; and the adopted classification algorithms all show good performance in terms of accuracy; moreover, KNN has the lowest complexity compared to the other three. The accuracy of KNN based on PN correlation is over 95% even when the SNR is below -5dB if the correlation gains of two neighbour frame headers are combined.

Please use this identifier to cite or link to this item:

http://hdl.handle.net/10453/158132