Maximum Focal Inter-Class Angular Loss with Norm Constraint for Automatic Modulation Classification

Zhang, S; Fu, J; Zhang, Z; Yu, S; Mao, S; Lin, Y

Maximum Focal Inter-Class Angular Loss with Norm Constraint for Automatic Modulation Classification

Zhang, S Fu, J Zhang, Z Yu, S

Mao, S Lin, Y

Permalink

Publisher:: Institute of Electrical and Electronics Engineers (IEEE)
Publication Type:: Conference Proceeding
Citation:: GLOBECOM 2022 - 2022 IEEE Global Communications Conference, 2023, 00, pp. 5323-5328
Issue Date:: 2023-12-08

Closed Access

	Filename	Description	Size
	Maximum Focal Inter-Class Angular Loss.pdf	Supporting information	6.23 MB	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	Zhang, S
dc.contributor.author	Fu, J
dc.contributor.author	Zhang, Z
dc.contributor.author	Yu, S https://orcid.org/0000-0003-4485-6743
dc.contributor.author	Mao, S
dc.contributor.author	Lin, Y
dc.date	2022-12-04
dc.date.accessioned	2024-03-27T22:37:17Z
dc.date.available	2024-03-27T22:37:17Z
dc.date.issued	2023-12-08
dc.identifier.citation	GLOBECOM 2022 - 2022 IEEE Global Communications Conference, 2023, 00, pp. 5323-5328
dc.identifier.isbn	978-1-6654-3540-6
dc.identifier.issn	2334-0983
dc.identifier.issn	2576-6813
dc.identifier.uri	http://hdl.handle.net/10453/177290
dc.description.abstract	Artificial intelligence (AI) has emerged as the most promising solution expected to overcome the high degree of abstraction of radio signals and achieve accurate automatic modulation classification (AMC). To further improve the classification performance of the AMC model and enhance its interpretability, the network output layer is modeled as a decision space into which the input data is projected. In this paper, we expand the inter-class angle between the classes with the largest confusion rate to increase the decision space. In addition, we extend the perspective to the softmax layer and evaluate the negative impact of the output distribution range on the confidence difference in the AMC problem. We further propose constraining the norm of the input data to the output layer in combination with prior knowledge of the distribution of modulation signal data. Combining the above two aspects, a Maximum Focal Inter-Class Angular Loss with Norm Constraint (MFICAL-NC) scheme is proposed. The experimental results show that the method can guide the model to obtain a better fitting state and a stronger generalization ability.
dc.language	en
dc.publisher	Institute of Electrical and Electronics Engineers (IEEE)
dc.relation.ispartof	GLOBECOM 2022 - 2022 IEEE Global Communications Conference
dc.relation.ispartof	IEEE Global Communications Conference
dc.relation.ispartofseries	IEEE Global Communications Conference
dc.relation.isbasedon	10.1109/globecom48099.2022.10001441
dc.rights	info:eu-repo/semantics/closedAccess
dc.title	Maximum Focal Inter-Class Angular Loss with Norm Constraint for Automatic Modulation Classification
dc.type	Conference Proceeding
utslib.citation.volume	00
utslib.location.activity	Rio de Janeiro, Brazil
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
pubs.organisational-group	University of Technology Sydney/Strength - CCSP - Centre for Cyber Security and Privacy
utslib.copyright.status	closed_access	*
pubs.consider-herdc	true
dc.date.updated	2024-03-27T22:37:14Z
pubs.finish-date	2022-12-08
pubs.place-of-publication	Piscataway, USA
pubs.publication-status	Published
pubs.start-date	2022-12-04
pubs.volume	00
dc.location	Piscataway, USA

Abstract:

Artificial intelligence (AI) has emerged as the most promising solution expected to overcome the high degree of abstraction of radio signals and achieve accurate automatic modulation classification (AMC). To further improve the classification performance of the AMC model and enhance its interpretability, the network output layer is modeled as a decision space into which the input data is projected. In this paper, we expand the inter-class angle between the classes with the largest confusion rate to increase the decision space. In addition, we extend the perspective to the softmax layer and evaluate the negative impact of the output distribution range on the confidence difference in the AMC problem. We further propose constraining the norm of the input data to the output layer in combination with prior knowledge of the distribution of modulation signal data. Combining the above two aspects, a Maximum Focal Inter-Class Angular Loss with Norm Constraint (MFICAL-NC) scheme is proposed. The experimental results show that the method can guide the model to obtain a better fitting state and a stronger generalization ability.

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

http://hdl.handle.net/10453/177290