Machine learning-based signal degradation models for attenuated underwater optical communication OAM beams

OPTICS COMMUNICATIONS

卷:474

Article

Neary, Patrick L.¹  Watnik, Abbie T.²  Judd, K. Peter²  Lindle, James R.³  Flann, Nicholas S.¹ 

[1] Utah State Univ, Logan, UT 84322 USA

[2] Naval Res Lab, Washington, DC 20036 USA

[3] DCS Corp, Alexandria, VA 22310 USA

关键词: Convolutional neural networks;    Automatic differentiation;    Radon cumulative distribution transform;    Attenuation models;    Orbital angular momentum;    Underwater communications;    Physics-based training;   

DOI  :  10.1016/j.optcom.2020.126058

来源: Elsevier

【 摘 要 】

Signal attenuation in underwater communications is a problem that degrades classification performance. Several novel CNN-based (SMART) models are developed to capture the physics of the attenuation process. One model is built and trained using automatic differentiation and another uses the radon cumulative distribution transform. These models are inserted in the classifier training pipeline. It is shown that including these attenuation models in classifier training significantly improves classification performance when the trained model is tested with environmentally attenuated images. The improved classification accuracy will be important in future OAM underwater optical communication applications.

【 授权许可】

Free