Deep-learning neural network for MIMO detection in a mode-division multiplexed optical transmission system

Bishal Poudel; Joji Oshima; Hirokazu Kobayashi; Katsushi Iwashita

doi:10.1117/12.2505445

1 February 2019 Deep-learning neural network for MIMO detection in a mode-division multiplexed optical transmission system

Bishal Poudel, Joji Oshima, Hirokazu Kobayashi, Katsushi Iwashita

Author Affiliations +

Proceedings Volume 10947, Next-Generation Optical Communication: Components, Sub-Systems, and Systems VIII; 109470C (2019) https://doi.org/10.1117/12.2505445
Event: SPIE OPTO, 2019, San Francisco, California, United States

Abstract

In this paper, a Mode division multiplexing (MDM) optical transmission system that uses deep learning neural network (DLNN) for Multiple Input Multiple Output (MIMO) detection is presented. Two channels operating at 250Mbps are QPSK modulated and transmitted at different mode through a Multi-Mode fiber and successfully detected. For MIMO detection, a supervised DLNN, which is designed, trained and evaluated using a Keras library and TensorFlow, is implemented in this MDM optical transmission system. The performance of our DLNN for MIMO detection is compared with Zero Forcing and Semi-Definite Relaxation Row-by-Row detectors. Our DLNN outruns the performance of these MIMO detectors.

Conference Presentation

Citation Download Citation

Bishal Poudel, Joji Oshima, Hirokazu Kobayashi, and Katsushi Iwashita "Deep-learning neural network for MIMO detection in a mode-division multiplexed optical transmission system", Proc. SPIE 10947, Next-Generation Optical Communication: Components, Sub-Systems, and Systems VIII, 109470C (1 February 2019); https://doi.org/10.1117/12.2505445

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available