FULL-DAY TUTORIAL
Application of Deep Learning in Communications: 5G and Beyond - Hands On
Mode: Onsite - Full Day Course for signal processing and wireless communication enthusiasts
Abstract: Radio Frequency (RF) signal classification is a key technique of Dynamic Spectrum Access (DSA) to utilize the unused spectrum in Cognitive Radio (CR) to meet the ever-increasing traffic demands for the next generation 5G and beyond cellular networks. In recent years, the RF signal classification for CR-based applications using Deep Learning (DL) architectures has received considerable attention. This tutorial focuses on a DL-based framework with Convolution Neural Network (CNN) architecture for classifying various modulation schemes such as BPSK, QPSK and GMSK. The real-time GSM signals captured from the nearby base stations will be used to analyse the performance of the developed CNN architecture.
Learning Objectives: By the end of the tutorial, the participants shall be able,
- To use Kaggle platform for handling big RF datasets for DL-based wireless projects
- To learn Python programming tools for signal processing and DL
- To prepare, train, test and predict real-time wireless signals
- To build DL-based architectures for various wireless applications
10:00 AM - 11:30 AM: Fundamentals of Deep Learning and CNN architecture
11:30 AM - 01:00 PM: Introduction to Kaggle Platform, Basics of Python programming for Signal Processing and Deep Learning
01:00 PM - 02:00 PM: Lunch
02:00 PM - 03:00 PM: Dataset generation using Deep Radio™, GNU platform and Wi-Guy®
03:00 PM - 04:00 PM: Hands-on: CNN Model creation and model training
04:00 PM - 05:00 PM: Hands-on: Testing and prediction
Maximum Number of Attendees Participating: No limit.
Hands-On: The participants should possess laptop/computer with internet connection; An account in Kaggle platform (www.kaggle.com) is required; Basic knowledge of Digital Signal Processing and Wireless Communications will be an additional advantage.
Tutorial Speakers:
Dr. Prabhu Chandhar, Director, Chandhar Research Labs, Chennai, India.
Prabhu Chandhar received the Ph.D. degree from IIT Kharagpur, Kharagpur, India in 2015. From 2009 to 2010, he was a Senior Research Fellow at the Vodafone IIT KGP Centre of Excellence in Telecommunications, IIT Kharagpur. From 2015 to 2017, he was a Post- Doctoral Researcher at the Division of Communication Systems, Linköping University, Linköping, Sweden. Since 2018, he serves as the Director of Chandhar Research Labs, Chennai, India. His research interests are within the fields of Signal Processing and Communication Theory. https://bio.chandhar-labs.com Dr. Sathish Babu, Senior Researcher, Chandhar Research Labs, Chennai, India.
Sathish Babu received the Ph.D. degree from IIT Kharagpur in 2017. From 2010 to 2017, he worked as a Junior Project Officer handling sponsored research projects at Kalpana Chawla Space Technology Cell (KCSTC), IIT Kharagpur in collaboration with Indian Space Research Organization (ISRO) – Satellite Application Centre (SAC), Ahmedabad in field of satellite Navigation. From 2017 to 2019, he was working as an Adhoc Faculty at National Institute of Technology Karaikal, Puduchery. Since 2020, he works as a senior researcher at Chandhar Research Labs Pvt. Ltd., Chennai. His research interests includes Signal Processing and Communication for Next generation wireless systems, Machine Learning for RF and Satellite Navigation.
Intended Participants and Level: This tutorial is intended to undergraduate/postgraduate students, research scholars, faculty members, industry personnel, interested in learning and developing skills to conduct Deep Learning-based project/research works in the fields of advanced wireless communication technologies. Also, it will be more relevant for the participants with EEE, ECE, CSE and IT background.