CERTIFICATIONS

THESIS HIGHLIGHTS

 PhD Thesis Highlights

•         Title:  Edge Intelligence for 5G Network and Beyond

•         Institution: Ulster University, Belfast, United Kingdom

Research Objectives:

•         Investigate the role of AI in physical layer communication challenges.

•         Develop deep learning techniques for signal detection in MIMO systems, with a focus on future 6G wireless systems.

•         Analyzed trade-offs between performance and computational complexity to enable practical, real-time deployment of AI-driven signal detection methods.

Research Challenges:

•         Designing efficient AI methods for MIMO systems in B5G/6G environments.

•         Balancing complexity with latency and reliability to meet URLLC requirements.

•        Ensuring robustness across diverse and realistic channel conditions.

•        Achieving benchmark-level performance suitable for high-impact publication.

Key Contributions:

•         Developed multiple AI-based models for signal detection tailored for B5G/6G systems.

•         Introduced complexity-aware deep learning architectures for real-time and scalable deployment.

•         Enhanced model adaptability by incorporating channel imperfections and loss.

•         Validated efficiency through extensive simulations & comparison with state-of-the-art methods.

•         Published results in ISI-indexed Q1/Q2 journals and various IEEE conferences.

Master’s Thesis Highlights

•         Title: Community Detection-Based Link Failure Recovery in Software-Defined Networks

•         Institution: Universiti Teknologi PETRONAS, Malaysia

Research Objectives:

•         Design a novel routing failure recovery technique to address link failures in SDN.

•         Extend the solution to handle both single and multiple link failures in SDN.

•         Evaluate performance using different metrics under diverse simulated conditions.

Research Challenges:

•         Develop a scalable, adaptive routing algorithm for complex SDN environments.

•         Integrate the proposed method for real-time validation in OpenFlow-based SDNs.

•         Achieve measurable improvements over existing techniques and publishable results.

Key Contributions:

•         Developed a community detection-based algorithm for link failure recovery in SDN.

•         Demonstrated significant performance gains over benchmark techniques. 

CERTIFICATIONS

• Certification: First Steps to Teaching (FST) | Ulster University, Belfast, UK 

• Certification: Postgraduate Teaching Assistant (PGTA) | Ulster University, Belfast, UK

• Certification: Research Integrity | Ulster University, Belfast, UK 

• Certification: Research Methodology | Ulster University, UTP, Malaysia

• Certification: Basics of Machine Learning | Great Learning Academy

• Certification: Python for Machine Learning | Great Learning Academy