FRIDAY, 13 DECEMBER 2019 (FULL DAY) 9:00 am - 5:30 pm
Room: Queen's 5
Session Chairs: Elisabeth de Carvalho (Aalborg University, Denmark)
Session 1: Channel Modeling and channel – based classification
9:00 am – 10:30 am
Keynote Speech: Machine Learning in Communications: Where do we go from here?
Tim O’Shea (Virginia Tech, USA)
- Calibration of Stochastic Channel Models using Approximate Bayesian Computation
Ayush Bharti and Troels Pedersen (Aalborg University, Denmark) - Sign Language Gesture Recognition using Doppler Radar and Deep Learning
Hovannes K. Kulhandjian and Prakshi Sharma (California State University, Fresno, USA); Michel Kulhandjian (University of Ottawa & Carleton University, Canada); Claude D’Amours (University of Ottawa, Canada) - Toward Receiver-Agnostic RF Fingerprint Verification
Kevin Merchant (US Naval Research Laboratory, USA); Bryan Nousain (Naval Research Laboratory, USA)
Coffee Break: 10:30 am - 11:00 am
Session 2: Machine learning for physical Layer optimization
11:00 am - 12:30 pm
- Joint Learning of Geometric and Probabilistic Constellation Shaping
Maximilian Stark (Hamburg University of Technology, Germany); Fayçal Ait Aoudia and Jakob Hoydis (Nokia Bell Labs, France) - Deep Learning-Based Quantization of L-Values for Gray-Coded Modulation
Marius Arvinte (University of Texas at Austin, USA); Sriram Vishwanath (University of Texas Austin, USA); Ahmed Tewfik (University of Texas, Austin, USA) - Adaptive Modulation and Coding based on Reinforcement Learning for 5G Networks
Mateus Pontes Mota and Daniel Araújo (Federal University of Ceará, Brazil); Francisco Hugo Costa, Neto (Federal University of Ceará & Wireless Telecommunications Research Group, Brazil); André de Almeida (Federal University of Ceará & Wireless Telecom Research Group - GTEL, Brazil); Francisco R. P. Cavalcanti (Federal University of Ceará & GTEL - Wireless Telecom Research Group, Brazil) - "Machine LLRning": Learning to Softly Demodulate
Ori Shental (Bell Labs, USA); Jakob Hoydis (Nokia Bell Labs, France) - Deep Learning based Precoding for the MIMO Gaussian Wiretap Channel
Xinliang Zhang and Mojtaba Vaezi (Villanova University, USA) - Deep Learning-Aided Binary Visible Light Communication Systems
Hoon Lee (Pukyong National University, Korea); Tony Q. S. Quek (Singapore University of Technology and Design, Singapore); Sang Hyun Lee (Korea University, Korea)
Lunch Break: 12:30 pm - 2:00 pm
Session 3: Panel Session
2:00 pm - 3:30 pm
Panelists:
- Ahmed Alkhateeb, Assistant Professor, Arizona State University
- Jeff Andrews, Professor, University of Texas at Austin
- Marco Di Renzo, CNRS Research Director - CentraleSupelec, Paris-Saclay University
- Slawomir Stanczak, Professor, TU Berlin & Fraunhofer HHI
- Geoffery Ye Li, Professor, George Tech
Organizers:
- Elisabeth De Carvalho, Professor, Aalborg University
- Tim O'Shea, Assistant Professor, Virginia Tech & CTO DeepSig
Abstract: This panel will explore views and ideas on future promising areas and applications for ML in wireless communications systems, exploring where panelists feel are the nearest, most impactful, most proven, most unfounded and most challenging impact areas. We will attempt to understand where ML will have a major impact, and where and why it still falls short in other areas through a range of panel introductions, prompts, open questions, and subsequent discussions.
Coffee Break: 3:30 pm - 4:00 pm
Session 4: Machine learning for MAC and higher layer optimization
4:00 pm - 5:30 pm
- Machine Learning for Power Control in D2D Communication based on Cellular Channel Gains
Mehyar Najla (Czech Technical University in Prague, Czech Republic); David Gesbert (Eurecom Institute, France); Zdenek Becvar and Pavel Mach (Czech Technical University in Prague, Czech Republic) - A Graph Neural Network Approach for Scalable Wireless Power Control
Yifei Shen (The Hong Kong University of Science and Technology, Hong Kong); Yuanming Shi (ShanghaiTech University, P.R. China); Jun Zhang (The Hong Kong Polytechnic University, Hong Kong); Khaled B. Letaief (The Hong Kong University of Science and Technology, Hong Kong) - Managing Tropospheric Ducting Effect in Mobile Networks using Unsupervised Machine Learning
Mahmoud Nour (Vodafone Egypt, Egypt); Ahmed Naglah (University of Louisville, USA); Mostafa Essa (Vodafone & The American University in Cairo, Egypt) - A Reinforcement Learning Approach for the Multichannel Rendezvous Problem
Jen-Hung Wang, Ping-En Lu, Cheng-Shang Chang and Duan-Shin Lee (National Tsing Hua University, Taiwan) - Deep Reinforcement Learning for Demand-Aware Joint VNF Placement-and-Routing
Shaoyang Wang and Tiejun Lv (Beijing University of Posts and Telecommunications, P.R. China) - Learning to Branch-and-Bound for Header-free Communications
Yandong Shi and Yuanming Shi (ShanghaiTech University, P.R. China)
