Assist. Prof. Dr. Hafiz Muhammad Raza ur Rehman | Yeungnam University | South Korea
Author Profiles
Scopus
Orcid
Google Scholar
Early Academic Pursuits
Dr. Hafiz Muhammad Raza ur Rehman began his academic journey with a strong foundation in information and communication engineering, culminating in a PhD from Yeungnam University, Korea. His doctoral research laid the groundwork for his later contributions in machine learning, multi-agent reinforcement learning (MARL), and data-science. His academic excellence and early engagement with algorithmic design and optimization established his trajectory as a dedicated researcher and educator in computational intelligence.
Professional Endeavors
Following his doctoral studies, Dr. Raza ur Rehman pursued a postdoctoral research position in Korea, focusing on sensor calibration for autonomous vehicles (AVs). Over 5.5 months, he conducted high-level interdisciplinary work aimed at improving the precision and reliability of AV sensor systems. He also gained substantial teaching experience 9 months as an Assistant Professor where he taught undergraduate and graduate courses in machine learning, deep learning, reinforcement learning, and data-science. In addition, his collaboration with the Electronics and Telecommunications Research Institute (ETRI), Korea, on a US Air Force–funded project, exemplified his ability to contribute to large-scale international research efforts.
Contributions and Research Focus
Dr. Raza ur Rehman’s research portfolio reflects a deep commitment to innovation and interdisciplinary integration. His primary focus areas include multi-agent reinforcement learning (MARL), autonomous vehicle systems, natural language processing (NLP), and optimization algorithms. He has authored a patent centered on MARL techniques and published several impactful journal and conference papers. Key publications include “QsOD: MARL-based QMIX with Grey Wolf Optimization” and “Prediction-Based Model for Chemical Compounds.” Moreover, he has presented research such as “Camera Calibration with CNN” at IEEE conferences and six additional papers at Korean academic venues. His current research extends to seven articles under review in internationally reputed journals, reinforcing his commitment to advancing data-science and intelligent systems.
Impact and Influence
Dr. Raza ur Rehman’s interdisciplinary research bridges theory and application spanning from algorithmic optimization to real-world technological integration. His MARL-related patent and publications contribute significantly to the growing body of knowledge in intelligent agent systems. By integrating data-science with advanced computational models, his work influences emerging fields such as autonomous navigation, machine learning-based control systems, and intelligent automation. As a mentor, he continues to inspire students through hands-on projects, fostering innovation and critical thinking in the next generation of engineers and researchers.
Academic Cites
His scholarly output includes publications in peer-reviewed international journals, conference presentations, and ongoing submissions to high-impact outlets. The QsOD study and the chemical compound prediction model have attracted interest in computational optimization and artificial intelligence research circles. His IEEE presentation on CNN-based camera calibration further strengthened his academic visibility and recognition within the AI research community.
Legacy and Future Contributions
Looking ahead, Dr. Hafiz Muhammad Raza ur Rehman aims to expand his research on multi-agent reinforcement learning, autonomous systems, and optimization-driven AI architectures. His future work is poised to contribute substantially to global research in data-science, particularly in developing adaptive, intelligent algorithms for complex real-world problems. Through continued teaching, mentorship, and publication, he aspires to leave a lasting legacy in both academia and applied research bridging the gap between theoretical innovation and practical technological advancement.
Featured Publications
Raza, S. N., ur Rehman, H. M., Lee, S. G., & Choi, G. S. (2019). Artificial intelligence-based camera calibration. 2019 15th International Wireless Communications & Mobile Computing Conference (IWCMC), 32. IEEE.
Nagulapati, V. M., ur Rehman, H. M. R., Haider, J., Qyyum, M. A., Choi, G. S., & Lim, H. (2022). Hybrid machine learning-based model for solubilities prediction of various gases in deep eutectic solvent for rigorous process design of hydrogen purification. Separation and Purification Technology, 298, 121651.
ur Rehman, H. M. R., On, B. W., Ningombam, D. D., Yi, S., & Choi, G. S. (2021). QSOD: Hybrid policy gradient for deep multi-agent reinforcement learning. IEEE Access, 9, 129728–129741.
ur Rehman, H. M. R., Saleem, M., Jhandir, M. Z., & Hafiz, H. G. I. A. (2025). Detecting hate in diversity: A survey of multilingual code-mixed image and video analysis. Journal of Big Data, 12(1), Article 5.
Younas, R., ur Rehman, H. M. R., Lee, I., On, B. W., Yi, S., & Choi, G. S. (2025). Sa-MARL: Novel self-attention-based multi-agent reinforcement learning with stochastic gradient descent. IEEE Access, 13, Article 5.
Khan, N. U., & ur Rehman, H. M. R. (2025). Real time signal decoding in closed loop brain computer interface for cognitive modulation. Ubiquitous Technology Journal, 1(1), 32–39.
ur Rehman, H. M. R., Haider, S. A., Faisal, H., Yoo, K. Y., Jhandir, M. Z., & Choi, G. S. (2025). A novel framework for Saraiki script recognition using advanced machine learning models (YOLOv8 and CNN). IEEE Access, 13, Article 2.