Semi-supervised Learning Enabled Scalable High-Spatial-Density Channel Multiplexing over Multimode Fibers
- Resource Type
- Conference
- Authors
- Fan, Pengfei; Ruddlesden, Michael; Wang, Yufei; Zhao, Luming; Lu, Chao; Su, Lei
- Source
- 2022 27th OptoElectronics and Communications Conference (OECC) and 2022 International Conference on Photonics in Switching and Computing (PSC) OptoElectronics and Communications Conference (OECC) and 2022 International Conference on Photonics in Switching and Computing (PSC), 2022 27th. :1-4 Jul, 2022
- Subject
- Communication, Networking and Broadcast Technologies
Components, Circuits, Devices and Systems
Fields, Waves and Electromagnetics
Photonics and Electrooptics
Signal Processing and Analysis
Multiplexing
Deep learning
Optical switches
Semisupervised learning
Optical fiber networks
Speckle
Optics
deep neural network
fiber optics communications
adaptive semi-supervised learning method
space-division multiplexing
- Language
We proposed a semi-supervised confidence-based learning approach (SCALA) to overcome the high-temporal-variability of multimode fiber (MMF) information channels, and experimentally demonstrated continuous transmission of high-spatial-density information with accuracy close to 100% over different MMFs.