TY - JOUR
T1 - Learning Enabled Continuous Transmission of Spatially Distributed Information through Multimode Fibers
AU - Fan, Pengfei
AU - Ruddlesden, Michael
AU - Wang, Yufei
AU - Zhao, Luming
AU - Lu, Chao
AU - Su, Lei
N1 - Funding Information:
This research was supported by Engineering and Physical Sciences Research Council (EP/L022559/1, EP/L022559/2), Royal Society (RG130230, IE161214) and H2020 Marie Skłodowska‐Curie Actions (790666). This research utilized Queen Mary's Apocrita HPC facility, supported by QMUL Research‐IT ( http://doi.org/10.5281/zenodo.438045 ).
Funding Information:
This research was supported by Engineering and Physical Sciences Research Council (EP/L022559/1, EP/L022559/2), Royal Society (RG130230, IE161214) and H2020 Marie Sk?odowska-Curie Actions (790666). This research utilized Queen Mary's Apocrita HPC facility, supported by QMUL Research-IT (http://doi.org/10.5281/zenodo.438045).
Publisher Copyright:
© 2021 The Authors. Laser & Photonics Reviews published by Wiley-VCH GmbH
PY - 2021/4
Y1 - 2021/4
N2 - Multimode fibers (MMF) are high-capacity channels and are promising to transmit spatially distributed information, such as an image. However, continuous transmission of randomly distributed information at a high-spatial density is still a challenge. Here, a high-spatial-density information transmission framework employing deep learning for MMFs is proposed. A proof-of-concept experimental system is presented to demonstrate up to 400-channel simultaneous data transmission with accuracy close to 100% over MMFs of different types, diameters, and lengths. A scalable semi-supervised learning model is proposed to adapt the convolutional neural network to the time-varying MMF information channels in real-time to overcome the instabilities in the lab environment. The preliminary results suggest that deep learning has the potential to maximize the use of the spatial dimension of MMFs for data transmission.
AB - Multimode fibers (MMF) are high-capacity channels and are promising to transmit spatially distributed information, such as an image. However, continuous transmission of randomly distributed information at a high-spatial density is still a challenge. Here, a high-spatial-density information transmission framework employing deep learning for MMFs is proposed. A proof-of-concept experimental system is presented to demonstrate up to 400-channel simultaneous data transmission with accuracy close to 100% over MMFs of different types, diameters, and lengths. A scalable semi-supervised learning model is proposed to adapt the convolutional neural network to the time-varying MMF information channels in real-time to overcome the instabilities in the lab environment. The preliminary results suggest that deep learning has the potential to maximize the use of the spatial dimension of MMFs for data transmission.
KW - deep learning
KW - information transmission
KW - multimode optical fibers
KW - neural networks
KW - single multimode fiber imaging
UR - http://www.scopus.com/inward/record.url?scp=85101328199&partnerID=8YFLogxK
U2 - 10.1002/lpor.202000348
DO - 10.1002/lpor.202000348
M3 - Journal article
AN - SCOPUS:85101328199
SN - 1863-8880
VL - 15
JO - Laser and Photonics Reviews
JF - Laser and Photonics Reviews
IS - 4
M1 - 2000348
ER -