Problem
Research questions and friction points this paper is trying to address.
Semantic Communication
Optical Fiber Communication
Wavelength-Division Multiplexing
Image Classification
Nonlinear Channel
End-to-End Optical Semantic Communication over a Nonlinear WDM Fiber Link
🤖 AI Summary
This study addresses the limitations in transmission efficiency and reach imposed by bit-level fidelity requirements in optical networks by proposing an end-to-end optical semantic communication system tailored for inference and control tasks. Abandoning conventional explicit source compression and channel coding, the system directly maps images to channel symbols, preserving only task-relevant information. By integrating nonlinear wavelength-division multiplexing (WDM) fiber channel modeling, multi-order QAM modulation, and end-to-end deep learning, it achieves joint classification and reconstruction. Experimental results on the MNIST dataset demonstrate a classification accuracy exceeding 98.9%, while requiring significantly fewer transmitted symbols than an LDPC-JPEG baseline. These findings effectively validate the proposed system’s advantages in extending transmission distance and reducing resource consumption.
📝 Abstract
Emerging optical-network applications increasingly use received data for inference and control rather than exact source reproduction, creating an opportunity to trade bit-level fidelity for greater transmission reach and efficiency. We propose an end-to-end optical semantic communication system for joint image classification and reconstruction over a nonlinear wavelength-division multiplexed (WDM) fiber channel. The system maps each image directly into a fixed-length sequence of channel symbols that preserves task-relevant information, without explicit source compression or channel coding. Experiments on the MNIST dataset cover launch powers from -9 to +3 dBm, fiber lengths up to 800 km, and 16-, 64-, and 256-Quadrature Amplitude Modulation (QAM) formats. At 0 dBm, classification accuracy remains between 98.92% and 99.31% across all tested link lengths and modulation orders, while requiring fewer transmitted symbols than a Low-Density Parity-Check (LDPC)-coded JPEG baseline at every tested modulation order. These results show that semantic communication can simultaneously extend optical reach and reduce transmission resources by conveying only task-relevant information.
Innovation
Methods, ideas, or system contributions that make the work stand out.
Semantic Communication
End-to-End Learning
Wavelength-Division Multiplexing
Nonlinear Fiber Channel
Joint Source-Channel Coding
🔎 Similar Papers
No similar papers found.
