Semantic communication improves image transmission over long fiber links
End-to-End Optical Semantic Communication over a Nonlinear WDM Fiber Link
Information TheoryMachine Learning
Summary
Sending images over fiber-optic cables usually focuses on exact copies, which can limit how far data travels. This paper shows a way to send images that keeps only important parts needed for tasks like recognizing the image, not every detail. The authors created a system that sends images directly as signals optimized for recognition and reconstruction, even over long distances and with tricky interference. Their experiments demonstrated high accuracy and fewer symbols sent compared to traditional methods, making transmission more efficient.
What this means in practice
- •For fiber network operators: Extend the distance and efficiency of optical links by transmitting only task-relevant image data without full compression or error correction overhead.
- •For autonomous vehicle teams: Use efficient optical links to support image recognition tasks in sensor networks relying on long-distance fiber communication.
Authors
Hussein Jammal, Andrea Bianco, Cristina Rottondi
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.