Christine Tremblay is a full professor with the Department of Electrical Engineering at the École de technologie supérieure (ÉTS) in Montreal. She received the B.S. degree in engineering physics from Université Laval, in 1984, the M.Sc. degree from the Institut National de la Recherche Scientifique Énergie, in 1985, and the Ph.D. degree in optoelectronics from the École Polytechnique de Montréal, in 1992. She was a Research Scientist with the National Optics Institute from 1991 to 1998, where she conducted research on integrated optical devices for communication and sensing applications. From 1998 to 2004, she held senior research and development and technology management positions for several organizations. As an Engineering Manager at EXFO and the Director of Engineering at Roctest, she was responsible for the development of fiber-optic test equipment. She also served as a Product Manager at Nortel for Dense Wavelength Division Multiplexing Systems. She is the Founding Researcher and the Head of the Network Technology Laboratory. She is currently Assistant Director for the Ph.D. Program at the ÉTS. She is a member of the Optical Society of America, the IEEE Photonics Society, and STARaCom and COPL Strategic Clusters. She has been a Co-Instructor for two hands-on courses of the Optical Society of America on optical fiber and polarization measurements (2009 – 2015). Her research interests include machine learning for optical networking applications, filterless optical networking, performance monitoring, optical layer characterization and modeling, and silicon photonics devices.
Her program as part of O’COMEX working group :
To join the conference from your system, please read the following instructions : Video Conference
- June, 25 2019 – 14hs – 15hs
- Place: Telecom SudParis – Batiment principal – 9, Rue Charles Fourier – 91011 Evry
- Room : C305 – 3ème étage – aile C
- Title: Machine learning for optical networking applications
- Abstract: The objective of this presentation is to illustrate how machine learning (ML) can be used in optical networking through two application examples. In the first part, we will show the quality of transmission can be estimated before lightpath establishment using ML methods such as k-nearest neighbors, random forest and support vector machine. In the second part, we will illustrate how the long short term memory method can be used for performance prediction after lightpath establishment.
- Content:
- i) Machine learning concepts;
- ii) Quality of transmission (QoT) of unestablished lightpaths;
- iii) Performance prediction of established lightpaths;
- iv) Performance analysis;
- v) Discussion and conclusions.
- References:
- Tremblay, C., Allogba, S., Aladin, S., « Quality of Transmission Estimation and Performance Prediction of Lightpaths Using Machine Learning », to be presented at the 45th European Conference on Optical Communication (ECOC) (Dublin, Ireland, September 22-27, 2019), invited talk.
- Diaz-Montiel, A. A., Aladin, S., Tremblay, C., Ruffini, M., « Active Wavelength Load as a Feature for QoT Estimation Based on Support Vector Machine », to be presented at the IEEE International Conference on Communications (ICC) (Shanghai, China, May 20-24, 2019).
- Allogba, S., Tremblay, C., « K-Nearest Neighbors Classifier for Field Bit Error Rate Data », Asia Communications and Photonics Conference (ACP) (Hangzhou, China, Oct. 26-29, 2018), paper S4K.8.
- Tremblay, C., Aladin, S., « Machine Learning Techniques for Estimating the Quality of Transmission of Lightpaths », Proc. IEEE Photonics Society Summer Topical Meeting Series (SUM) (Waikoloa, USA, July 9-11, 2018), pages 237-238.
- Aladin, S, Tremblay, C., « Cognitive tool for estimating the QoT of new lightpaths ». Optical Fiber Communication Conference (OFC) (San Diego, CA, USA, Mar. 11-15, 2018), paper M3A.3.