Share Email Print

Proceedings Paper • new

Deep-learning neural network for MIMO detection in a mode-division multiplexed optical transmission system
Author(s): Bishal Poudel; Joji Oshima; Hirokazu Kobayashi; Katsushi Iwashita
Format Member Price Non-Member Price
PDF $17.00 $21.00
cover GOOD NEWS! Your organization subscribes to the SPIE Digital Library. You may be able to download this paper for free. Check Access

Paper 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.

Paper Details

Date Published: 1 February 2019
PDF: 6 pages
Proc. SPIE 10947, Next-Generation Optical Communication: Components, Sub-Systems, and Systems VIII, 109470C (1 February 2019); doi: 10.1117/12.2505445
Show Author Affiliations
Bishal Poudel, Kochi Univ. of Technology (Japan)
Joji Oshima, Kochi Univ. of Technology (Japan)
Hirokazu Kobayashi, Kochi Univ. of Technology (Japan)
Katsushi Iwashita, Kochi Univ. of Technology (Japan)

Published in SPIE Proceedings Vol. 10947:
Next-Generation Optical Communication: Components, Sub-Systems, and Systems VIII
Guifang Li; Xiang Zhou, Editor(s)

© SPIE. Terms of Use
Back to Top