Phase I Research Projects
Investigating Machine Learning Techniques in Performance Improvement for the Next Generation Wireless Networks
The aim of this research is to investigate effective data-driven ML techniques for 5G networks.
Team leads
5G Networks and Drone Navigation Algorithms
This project will investigate cooperative algorithms, leveraging Beyond Visual Line of Sight (BVLOS) drone communications using 5G networks.
Team leads
Michel Barbeau
- Professor and Director, School of Computer Science, Carleton University
- barbeau@scs.carleton.ca
- 613-520-2600 ext 1644
Navigation and Control of Drones over 5G networks: Enhanced communication and adaptive control
The goal in this project is to perform research for and provide solutions to navigation and control of drones over 5G networks.
Team leads
Michel Barbeau
- Professor and Director, School of Computer Science, Carleton University
- barbeau@scs.carleton.ca
- 613-520-2600 ext 1644
Channel Reconstruction for LTE/NR Performance Verification for Research and Leadership in Wireless Network
In this project, we propose developing a simulation tool to reconstruct temporal-spatial channels based on limited CSI feedback that has been collected from User Equipments (UEs) communicating over real networks.
Team leads
M-MIMO Channel Estimation using Distributed Machine Learning and Edge Computing Technologies
In this project we will evaluate the feasibility of applying Distributed Machine Learning combining edge computing technology to conduct channel estimation in 5G massive MIMO.
Team leads
Spectrum Sharing with Machine Learning
In this project, we will investigate the use of Machine Learning and Deep Learning for spectrum sharing applications in 5G systems.
Team leads
Midband Channel Propagation Stud
This project will combine a theoretically driven approach alongside analysis of field-collected uplink sounding reference signal data (SRS) transmitted by several user terminals (UEs).
Team leads
Low Latency High Precision DoA and NoS Estimation for Partially Connected and Fully Connected Hybrid OLLS Architectures
The project advances the joint estimation of Direction of Arrival and Number of Sources in Hybrid Analog and Digital beamforming, using innovative methods for improved accuracy in wireless applications.
Team leads
Co-Op Project: Anomaly Detection
The project uses VAE-LSTM learning models for anomaly detection in telecommunication networks, enhancing system understanding and improving root cause analysis in RAN test channels.
Team leads
Estimating End-User Throughput Using Service Provider Cell Traces Via Gradient Boosting
The thesis explores the use of a Regularized Gradient Boosting model to predict user throughput in 5G networks, by accurately imputing missing values in cell traces collected from service provider resources, thereby enabling efficient resource management.
