Unobtrusive activity monitoring based on fiber-optic Mach-Zehnder interferometer is proposed, employing deep bi-directional long short-term memory network, realizing three activities recognition with accuracy of 99.2% and resolution of 0.5s.

© 2018 The Author(s)

PDF Article
More Like This
Optical Performance Monitoring in Fiber-Optic Networks Enabled by Machine Learning Techniques

Faisal Nadeem Khan, Chao Lu, and Alan Pak Tao Lau
M2F.3 Optical Fiber Communication Conference (OFC) 2018

Towards the Use of Machine Learning in Setups for OAM Mode Excitation in Optical Fibers

Antonio Astorino, Jesper Glückstad, and Karsten Rottwitt
JTu2A.6 Frontiers in Optics (FiO) 2018

Application of Machine Learning Techniques in Fiber-Optic Communication Systems

Alan Pak Tao Lau, Faisal Nadeem Khan, Qirui Fan, and Chao Lu
SpW4G.1 Signal Processing in Photonic Communications (SPPCom) 2018


You do not have subscription access to this journal. Citation lists with outbound citation links are available to subscribers only. You may subscribe either as an Optica member, or as an authorized user of your institution.

Contact your librarian or system administrator
Login to access Optica Member Subscription