AIRG

Artificial Intelligence Research Group

(AIRG)

At the AI Research Group (AIRG), we address fundamental challenges in AI research, with a core focus on healthcare, as well as mobility, cybersecurity, blockchain, communications, the metaverse, and data science. Our mission is to advance AI methodologies, create scalable solutions, and foster interdisciplinary innovation.

Goals of the AIRG


  • Developing innovative AI-driven solutions to address complex challenges and optimize processes across various industries, focusing on healthcare.
  • Building strong collaborations with academia to foster knowledge exchange and interdisciplinary research, ensuring cutting-edge advancements in AI.
  • Attracting research grants to support innovative projects and expand the scope of our research across multiple sectors.
  • Connecting with government and industry partners to align our AI research with real-world needs, facilitating the development of impactful solutions and driving innovation in key industries.

Research Verticals

RIT Dubai's Artificial Intelligence Research Group (AIRG) leads cutting-edge research projects across diverse industries, driving innovation in industries such as
healthcare, energy, cybersecurity, blockchain, metaverse, mobility and communications.

Faculty

Jinane Mounsef

Chair of Electrical Engineering and Computing Sciences Department, Associate Professor of Electrical Engineering

Abdulla Ismail

Professor of Electrical Engineering

Wesam Almobaideen

Computing Sciences Coordinator, Professor of Electrical Engineering and Computing

Ioannis Karamitsos
Assistant Professor of Data Analytics

Omar Abdul Latif

Coordinator of Computing Sciences programs, Assistant Professor of Computing Sciences
04-3712052

Ali Assi

Assistant Professor of Computing Security

Mehtab Khurshid

Lecturer of Computing Sciences

Researchers

Abhilasha Singh

Abhilasha Singh

Postdoctoral Researcher, Electrical Engineering
axscad5@rit.edu

RIT Placeholder

Houssein Kanso

Graduate Research Assistant, Electrical Engineering
hk7653@g.rit.edu

Healthcare

Early Cervical Cancer Detection

Researcher: Dr. Jinane Mounsef
Collaborators: MBRU and WAI


Cervical cancer ranks as a leading cause of mortality among women, with the conventional pap smear-based detection posing significant challenges due to its labor-intensive and time consuming nature. This study explores how Artificial Intelligence (AI) technology can be integrated into cervical cancer diagnostics to alleviate the workload of pathologists by streamlining and improving the detection process.

Read More

Energy

Two-way Load Flow Analysis using Newton-Raphson and Neural Network Methods in Smart Grids

Researcher: Dr. Abdulla Ismail


This research presents a study of the optimal power flow for networked microgrids with multiple renewable energy sources (PV panels and wind turbines), storage systems, generators, and load. The OPF problem is performed using a conventional method and an Artificial Intelligence method. In this research, we investigated the performance of MGs system with renewable energy integration with focus on power flow studies.

Read More

Cybersecurity

Unsupervised Instance Matching in Knowledge Graphs Using GAN-Based Language Translation

Researcher: Dr. Wesam Almobaideen


The Instance Matching technique involves identifying instances across different Knowledge Graphs (KGs) that refer to the same real-world entity. This process typically requires significant time and effort, especially with large KGs.

Read More

Blockchain

Blockchain technology via the lens of smart contract and consensus protocols

Researcher: Dr. Ioannis Karamitsos


In this area, Dr. Ioannis studies the design and development of different platforms such as Ethereum and Hyperledger. Dr. Ioannis also designs smart contract conceptual model for different industries. Finally, he examines the post quantum security mechanisms for the blockchain area.

Metaverse

Metacities

Researcher: Dr. Ioannis Karamitsos


Dr. Ioannis is applying metaverse in different vertical industry sectors, especially the shift of the smart cities (real estate) to Metacities.

Mobility

Enhancing Mobile Localization with Visual-Semantic SLAM and Event Cameras for Robust Autonomous Navigation 

Researcher: Dr. Jinane Mounsef
Collaborators: Lebanese American University, University of Sharjah, BITS Pilani Dubai


Simultaneous Localization and Mapping (SLAM) is a key technology for mobile robots and autonomous systems, allowing them to navigate and map their environment. Traditional SLAM methods, which rely on standard visual inputs, often face challenges in dynamic or low-feature environments. This research investigates the integration of visual and semantic SLAM techniques, along with the use of event cameras, to create a more robust mobile localization system. Event cameras, which capture pixel-level changes in intensity at high temporal resolutions, provide significant advantages in fast-moving and low-light scenarios. By combining the high temporal accuracy of event cameras with visual SLAM, which tracks a robot's movement, and semantic SLAM, which assigns meaningful labels to objects and scenes, the system achieves enhanced localization accuracy and resilience. The fusion of these techniques allows for more reliable mobile localization, even in complex and challenging environments, improving the robustness of autonomous navigation systems in both indoor and outdoor applications.

Click here to view the paper

Enhancing Mobile Localization with Visual-Semantic SLAM and Event Cameras for Robust Autonomous Navigation

Communications

Using spiking neural networks (SNN) to optimize resource-scheduling for deploying network slices in 5G

Researcher: Dr. Omar Abdul Latif


In this ongoing project, we are utilizing SNN that provides low-power and event-driven features that fits perfectly with 5G network slicing requirements. The simulation results were published and good feedback was received. We are currently working on real-life implementation on 5G core that was acquired as part of the Digital Transformation Lab at RIT.


Enhancing Spectrum Utilization in 5G Private Networks Through AI-Driven Cognitive Radio Technology

Researcher: Dr. Omar Abdul Latif

The scarcity of available spectrum resources for 5G systems poses a significant challenge for the efficient operation of these networks. This research project aims to investigate the application of cognitive radio technology, which utilizes AI, for spectrum sharing in 5G private networks, with the goal of enhancing spectrum utilization, optimizing network performance, and enabling coexistence with other wireless systems.

Data Science

Graph theory mining on the generative adversarial networks (GANs) and on Generative AI

Researcher: Dr. Ioannis Karamitsos


Dr. Ioannis is working with Diffusion Models, on MLOps pipelines framework and the optimization of dynamic systems for Machine Learning.


Understanding the theory, algorithms, modeling and practical aspects

Researcher: Dr. Ioannis Karamitsos

Dr. Ioannis is working on producing entire ML pipelines improving the various components of large systems and producing high quality in the intersection of data science concepts and computation.


Unsupervised Instance Matching in Large-Scale Knowledge Graphs Using GANs and Shared-Latent Space Translation

Researcher: Dr. Ali Assi

The Instance Matching technique involves identifying instances across different Knowledge Graphs (KGs) that refer to the same real-world entity. This process typically requires significant time and effort, especially with large KGs. Traditionally, this problem is addressed in a supervised manner, where a set of corresponding instance pairs across different KGs is available. However, in real-world applications involving billions of instances, such sets are often incomplete, adversely affecting the recall score. To address this challenge, our proposal explores an unsupervised approach by representing the instance matching problem as a language translation task. This is achieved through the use of a shared-latent space based on Generative Adversarial Networks (GANs), which allows for effective matching even in the absence of complete paired instances.

AIRG Contact

Reach out if you'd like to learn more about
our work, activities, or explore collaboration opportunities with AIRG.

Jinane Mounsef
Chair of Electrical Engineering and Computing Sciences Department, Associate Professor of Electrical Engineering

Website last updated: March 26, 2025