Dr. Farajollah Tahernezhad-Javazm | University of York | United Kingdom
Dr. Farajollah Tahernezhad-Javazm is a researcher in computer science and mechatronics with expertise in reinforcement learning, brain-machine interfaces, and evolutionary algorithms. He earned his Ph.D. from Ulster University, UK, focusing on transforming multiobjective evolutionary algorithms using hybrid structures and reinforcement learning. He currently serves as a Research Associate at the University of York, contributing to bio-inspired engineering design through Graph Neural Networks and Cartesian Genetic Programming. His previous roles include data analytics research at the University of Lincoln, a visiting Ph.D. position at Auburn University, and neuroimaging research at Ulster’s MEG lab. His interdisciplinary work spans AI, optimization, and neural signal processing.
Author Profiles
GOOGLE SCHOLAR | ORCID | SCOPUS
Early Academic Pursuits
Dr. Farajollah Tahernezhad-Javazm’s academic foundation is rooted in electronics and mechatronics engineering, disciplines that enabled him to engage early with complex systems and intelligent interfaces. He earned his BSc in Electronics Engineering from Yazd University in 2013, where he designed a programmable Building Management System (BMS). He progressed to an MSc in Mechatronics Engineering from the University of Tabriz in 2016, focusing on real-time brain-machine interface (BMI) systems using combinatorial classification methods. His academic trajectory culminated with a PhD in Computer Science from Ulster University, Northern Ireland, in May 2024. His doctoral thesis, “Reinforcement Learning and Hybrid Structures: Transforming Multiobjective Evolutionary Algorithms,” under the supervision of Prof. Damien Coyle and Dr. Debbie Rankin, integrated reinforcement learning with evolutionary computation, setting a strong theoretical and practical foundation for his future contributions to Experimental Physics and intelligent systems.
Professional Endeavors
Dr. Tahernezhad-Javazm has held numerous interdisciplinary roles across academia and research institutions. As a Research Associate at the University of York since November 2024, he contributes to the Re-Imagining Engineering Design (RIED) project, advancing bio-inspired methodologies using Graph Neural Networks (GNN), Cartesian Genetic Programming (CGP), and Reinforcement Learning (RL). Previously, at the University of Lincoln (2023–2024), he applied machine learning for data analytics in the food supply chain sector. His international research engagement includes time as a Visiting PhD Researcher at Auburn University in the U.S., working on multiobjective algorithms and reinforcement learning, and as a Research Assistant at Ulster University’s Magnetoencephalography (MEG) Laboratory, where he played a crucial role in managing high-sensitivity brain imaging systems contributing directly to Experimental Physics through real-time neuroimaging calibration, testing, and maintenance.
Contributions and Research Focus
Dr. Tahernezhad-Javazm’s research blends machine learning, neuroengineering, reinforcement learning, and optimization. His primary focus lies in developing hybrid intelligence systems to solve real-world challenges in Experimental Physics and computational design. His contributions span the development of AI-powered BMIs, reinforcement learning-enhanced evolutionary algorithms, and advanced sensor systems used in neuroimaging and engineering design. His work integrates data-driven modeling with bio-inspired computation, making significant inroads in signal decoding, system optimization, and neural data interpretation.
Impact and Influence
Through interdisciplinary collaborations in the UK, Iran, and the U.S., Dr. Tahernezhad-Javazm has advanced impactful methodologies in both engineering and Experimental Physics. His influence is evident in his work with high-profile teams like Prof. Andy Tyrrell’s group at the University of York and Prof. Alice E. Smith’s group at Auburn University. He bridges computational sciences with experimental applications particularly in bioengineering, neuroimaging, and smart system design. His MEG research also supports cognitive neuroscience by ensuring accurate and calibrated data collection, which is critical to the experimental integrity of advanced physics-driven medical systems.
Academic Cites
Dr. Tahernezhad-Javazm’s academic contributions have been published and cited across several interdisciplinary fields, including intelligent systems, optimization algorithms, and computational neuroscience. His work has been featured in machine learning conferences and neuroscience venues, particularly those focusing on Experimental Physics and real-time brain-machine interface systems. His publications reflect an evolving and impactful research profile with applications in healthcare, manufacturing, and engineering design.
Legacy and Future Contributions
Dr. Farajollah Tahernezhad-Javazm is on a promising trajectory to become a leading figure in AI-driven research with applications in Experimental Physics. With his experience across disciplines from brain-computer interfaces to evolutionary design he is poised to develop the next generation of adaptive, learning-based systems for real-world problems. His future work will likely explore deeper integration of physical sensor data with AI for predictive diagnostics, smart engineering systems, and dynamic experimentation frameworks. His legacy will be defined by a commitment to bridging machine learning with experimental sciences for enhanced innovation and societal impact.
Experimental Physics
Dr. Tahernezhad-Javazm’s research actively contributes to Experimental Physics through MEG calibration systems, real-time brain-machine interface innovations, and AI-driven optimization. His hybrid models enhance algorithmic performance in domains rooted in Experimental Physics, especially in neurotechnology and intelligent systems. The intersection of machine learning, signal processing, and physical experimentation in his research will continue to shape developments in Experimental Physics for years to come.
Notable Publications
Mapping the path to decarbonised agri-food products: A hybrid geographic information system and life cycle inventory methodology for assessing sustainable agriculture
Authors: W. Martindale, A. Saeidan, F. Tahernezhad-Javazm, T.Æ. Hollands, L. Duong, ...
Journal: International Journal of Food Science and Technology
Year: 2024
Citations: 2
R2 Indicator and Deep Reinforcement Learning Enhanced Adaptive Multi-Objective Evolutionary Algorithm
Authors: F. Tahernezhad-Javazm, D. Rankin, N. Du Bois, A.E. Smith, D. Coyle
Journal: arXiv preprint
Year: 2024
Citations: 1
R2-HMEWO: Hybrid multi-objective evolutionary algorithm based on the Equilibrium Optimizer and Whale Optimization Algorithm
Authors: F. Tahernezhad-Javazm, D. Rankin, D. Coyle
Conference: IEEE World Congress on Computational Intelligence
Year: 2022
Citations: 8
A Hybrid Multi-Objective Teaching Learning-Based Optimization Using Reference Points and R2 Indicator
Authors: F. Tahernezhad-Javazm, D. Rankin, D. Coyle
Conference: International Conference on Intelligent Systems, Metaheuristics & Swarm Intelligence
Year: 2022
Citations: 2
Ontology based information integration: A survey
Authors: M. Alizadeh, M.H. Shahrezaei, F. Tahernezhad-Javazm
Journal: arXiv preprint
Year: 2019
Citations: 9