PSC: A Packet Semantic Communication Framework for Lossy Transmission With Packet Loss Channel

Wenyu Zhang; Zhiwei Xie; Sherali Zeadally; Kaiyuan Bai; Hua Shao; Haijun Zhang; Victor C.M. Leung

doi:10.1109/LCOMM.2025.3587319

PSC: A Packet Semantic Communication Framework for Lossy Transmission With Packet Loss Channel

Wenyu Zhang
, Zhiwei Xie
, Sherali Zeadally
, Kaiyuan Bai
, Hua Shao
, Haijun Zhang
, Victor C.M. Leung

School of Information Science

Producción científica: Article › revisión exhaustiva

1 Cita (Scopus)

Resumen

Currently, semantic communication is predominantly confined to wireless communication scenarios, but not the general scenarios that transmit data packets. We propose packet semantic communication (PSC), a new semantic communication framework which achieves reliable transmissions in networks with packet loss. PSC works at the application layer, and it encodes the source data as binary data bits by using deep joint source-channel coding (DeepJSCC) and entropy coding, then transmits data as packets, and the decoder at the receiver performs the decoding process even when the packets are partially lost. We implement the proposed PSC for image transmission with a packet loss channel and compare its performance with the conventional better portable graphics (BPG) codec and learned image compression (LIC) model. The results obtained show that BPG and LIC are highly vulnerable to packet loss, but the proposed PSC can achieve strong robustness against packet loss, even when the packet loss rate (PLR) is as high as 80%.

Idioma original	English
Páginas (desde-hasta)	2113-2117
Número de páginas	5
Publicación	IEEE Communications Letters
Volumen	29
N.º	9
DOI	https://doi.org/10.1109/LCOMM.2025.3587319
Estado	Published - 2025

Nota bibliográfica

Publisher Copyright:
© 1997-2012 IEEE.

Financiación

Received 21 June 2025; revised 5 July 2025; accepted 6 July 2025. Date of publication 10 July 2025; date of current version 12 September 2025. This work was supported in part by the National Natural Science Foundation of China under Grant 62102021, in part by the National Natural Science Foundation of China under Grant 62101030, and in part by the Fundamental Research Funds for the Central Universities of USTB under Grant FRF-IDRY-20-020. The associate editor coordinating the review of this letter and approving it for publication was S. A. Tegos. (Corresponding author: Zhiwei Xie.) Wenyu Zhang, Zhiwei Xie, and Hua Shao are with the School of Intelligence Science and Technology and the Institute of Artificial Intelligence, University of Science and Technology Beijing, Beijing 100083, China (e-mail: [email protected]; [email protected]; [email protected]).

Financiadores	Número del financiador
National Natural Science Foundation of China (NSFC)	62102021, 62101030
Fundamental Research Funds for the Central Universities	FRF-IDRY-20-020

ASJC Scopus subject areas

Modeling and Simulation
Computer Science Applications
Electrical and Electronic Engineering

Acceder al documento

10.1109/LCOMM.2025.3587319

Otros archivos y enlaces

Citar esto

@article{fbe612dd004f4d89b45998515fe5ce08,

title = "PSC: A Packet Semantic Communication Framework for Lossy Transmission With Packet Loss Channel",

abstract = "Currently, semantic communication is predominantly confined to wireless communication scenarios, but not the general scenarios that transmit data packets. We propose packet semantic communication (PSC), a new semantic communication framework which achieves reliable transmissions in networks with packet loss. PSC works at the application layer, and it encodes the source data as binary data bits by using deep joint source-channel coding (DeepJSCC) and entropy coding, then transmits data as packets, and the decoder at the receiver performs the decoding process even when the packets are partially lost. We implement the proposed PSC for image transmission with a packet loss channel and compare its performance with the conventional better portable graphics (BPG) codec and learned image compression (LIC) model. The results obtained show that BPG and LIC are highly vulnerable to packet loss, but the proposed PSC can achieve strong robustness against packet loss, even when the packet loss rate (PLR) is as high as 80\%.",

keywords = "Deep joint source-channel coding, entropy coding, lossy transmission, packet semantic communication",

author = "Wenyu Zhang and Zhiwei Xie and Sherali Zeadally and Kaiyuan Bai and Hua Shao and Haijun Zhang and Leung, \{Victor C.M.\}",

note = "Publisher Copyright: {\textcopyright} 1997-2012 IEEE.",

year = "2025",

doi = "10.1109/LCOMM.2025.3587319",

language = "English",

volume = "29",

pages = "2113--2117",

number = "9",

}

TY - JOUR

T1 - PSC

T2 - A Packet Semantic Communication Framework for Lossy Transmission With Packet Loss Channel

AU - Zhang, Wenyu

AU - Xie, Zhiwei

AU - Zeadally, Sherali

AU - Bai, Kaiyuan

AU - Shao, Hua

AU - Zhang, Haijun

AU - Leung, Victor C.M.

PY - 2025

Y1 - 2025

N2 - Currently, semantic communication is predominantly confined to wireless communication scenarios, but not the general scenarios that transmit data packets. We propose packet semantic communication (PSC), a new semantic communication framework which achieves reliable transmissions in networks with packet loss. PSC works at the application layer, and it encodes the source data as binary data bits by using deep joint source-channel coding (DeepJSCC) and entropy coding, then transmits data as packets, and the decoder at the receiver performs the decoding process even when the packets are partially lost. We implement the proposed PSC for image transmission with a packet loss channel and compare its performance with the conventional better portable graphics (BPG) codec and learned image compression (LIC) model. The results obtained show that BPG and LIC are highly vulnerable to packet loss, but the proposed PSC can achieve strong robustness against packet loss, even when the packet loss rate (PLR) is as high as 80%.

AB - Currently, semantic communication is predominantly confined to wireless communication scenarios, but not the general scenarios that transmit data packets. We propose packet semantic communication (PSC), a new semantic communication framework which achieves reliable transmissions in networks with packet loss. PSC works at the application layer, and it encodes the source data as binary data bits by using deep joint source-channel coding (DeepJSCC) and entropy coding, then transmits data as packets, and the decoder at the receiver performs the decoding process even when the packets are partially lost. We implement the proposed PSC for image transmission with a packet loss channel and compare its performance with the conventional better portable graphics (BPG) codec and learned image compression (LIC) model. The results obtained show that BPG and LIC are highly vulnerable to packet loss, but the proposed PSC can achieve strong robustness against packet loss, even when the packet loss rate (PLR) is as high as 80%.

KW - Deep joint source-channel coding

KW - entropy coding

KW - lossy transmission

KW - packet semantic communication

UR - https://www.scopus.com/pages/publications/105010187332

UR - https://www.scopus.com/pages/publications/105010187332#tab=citedBy

U2 - 10.1109/LCOMM.2025.3587319

DO - 10.1109/LCOMM.2025.3587319

M3 - Article

AN - SCOPUS:105010187332

SN - 1089-7798

VL - 29

SP - 2113

EP - 2117

JO - IEEE Communications Letters

JF - IEEE Communications Letters

IS - 9

ER -

PSC: A Packet Semantic Communication Framework for Lossy Transmission With Packet Loss Channel

Resumen

Nota bibliográfica

Financiación

ASJC Scopus subject areas

Acceder al documento

Otros archivos y enlaces

Huella

Citar esto