Skip to main content

Faculty of Business and Information Technology Project Summaries

Supervisors  

Amirali Abari | Khalil El-Khatib

 

Supervisor name: Amirali Abari

Project title: Graph Neural Networks for Recommender Systems

Summary of research project: Recommender systems are prevalent in our day-to-day lives. They intelligently recommend desirable options to us (e.g., books on Amazon, movies on Netflix, etc.), which are consistent with our own taste or preferences. Several recent developments have been made in applying deep learning in recommender systems. A promising direction is to utilize graph embedding and graph convolutional networks, empowering recommender systems with graph-structured side information (e.g., social networks). Our goal is to develop practical deep learning algorithms for large-scale recommender systems in the presence of graph-structured side information.

Student responsibilities/tasks:

  • The Student is expected to review the relevant research literature along with other team members.
  • The Student will also be heavily involved in the development of the AI technologies and will co-author the consequent paper written from their involvement in this Project.
  • This Project provides a unique opportunity for the candidate to foster their knowledge in AI, graph neural networks and deep learning.

Student qualifications required:

  • The Student is expected to have familiarity with PyTorch and Deep Learning and be excellent in programming in Python.

Expected training/skills to be received by the Student:

  • Graph Neural Networks
  • Programming in PyG
  • Literature Review
  • Academic Writing

Length of award: 16 Weeks

Location of award: In-Person

Available Award: NSERC USRA or Ontario Tech STAR

 

Supervisor name: Khalil El-Khatib

Project title: Building a Multi-Level Intrusion Detection System

Summary of research project: Small Modular Reactors (SMRs) represent an innovative approach to nuclear power generation, boasting a smaller capacity, typically less than 300 MWe. In contrast to conventional nuclear power plants (NPPs), SMRs undergo manufacturing and assembly in industrial settings before transportation to the installation site. The evolution of SMRs from NPPs brings forth distinct cybersecurity threats. In this project, we aim to analyze potential cyber threats specific to Small Modular Reactors (SMRs). We will explore federated learning-based approaches to build multi-level AI-based intrusion detection systems.

Student responsibilities/tasks:

  • Read few research papers and prepare a summary report the state of art of cybersecurity for SMR.
  • Build an AI model for intrusion detection based on synthetic data for SMR.
  • Evaluate the performance of the model.
  • Extend the model to build a hierarchical model of the intrusion detection system.
  • Evaluate the performance of the hierarchical model.

Student qualifications required:

  • The Student should have taken a machine learning course with an A/A+ grade and have a strong understanding of networking and security principles.
  • The Student should also have strong analytics and communication skills.

Expected training/skills to be received by the Student:

  • How to do proper literature review
  • How to create synthetic data for SMR
  • How to run machine learning models on large data sets
  • Evaluate results from the execution of the machine learning models.

Length of award: 16 Weeks

Location of award: Hybrid

Available Award: NSERC USRA or Ontario Tech STAR