Gabriel Osei Forkuo | Machine Learning | Best Researcher Award

Posted on by sciencefather

Mr. Gabriel Osei Forkuo | Machine Learning | Best Researcher Award

Doctoral Researcher/ Research Assistant at Transilvania University of Brasov, Romania

Gabriel Osei Forkuo is a dedicated forestry specialist and researcher with an extensive background in forest operations engineering, postural ergonomics, and machine learning applications. He has built a career that merges practical field experience with academic research, contributing significantly to the development of innovative and cost-effective technologies in forest monitoring and conservation. Currently pursuing a Ph.D. in Forest Operations Engineering at Transilvania University of Brasov, Romania, Gabriel has emerged as a leading figure in the exploration of low-cost LiDAR technologies and smart solutions for ergonomic assessments in forestry. His multifaceted expertise is grounded in over two decades of professional service in teaching, field operations, and advanced scientific investigations.

Profile

Orcid

Education

Gabriel’s educational journey is marked by academic excellence and a continuous drive for specialized knowledge. He is currently enrolled in a Ph.D. program in Forest Operations Engineering at Transilvania University of Brasov, where his research focuses on integrating machine learning and computer vision for ergonomic assessments in forest operations. He previously earned a Master’s degree in Multiple Purpose Forestry from the same university, achieving excellent grades and a cumulative ECTS average of 9.76. His foundational studies include a Bachelor of Science degree in Natural Resources Management from Kwame Nkrumah University of Science and Technology, Kumasi, Ghana, where he graduated with First Class Honours. Earlier academic milestones include completing his GCE A-Level in science subjects and his GCE O-Level in science, supported by performance scholarships recognizing his consistent academic distinction.

Experience

Gabriel’s professional experience spans across teaching, research, and forest management. Between 2002 and 2011, he worked as a Forest Range Manager and Supervisor at the Forestry Commission Ghana, where he was instrumental in nursery planning, restoration of degraded forests, and report writing. From 1999 to 2001, he served as a Science and Maths Teacher at Maria Montessori School in Kumasi, followed by a role as a Teaching Assistant at his alma mater, Kwame Nkrumah University of Science and Technology. In this capacity, he conducted laboratory classes, supervised research data collection, and participated in academic presentations, establishing a strong foundation in both pedagogical and research methodologies. His leadership in afforestation programs and practical forest management further reflects his field-based competency and organizational capability.

Research Interest

Gabriel’s research interests are centered on forest operations engineering, with a special focus on postural ergonomics, machine learning applications, and smart technologies for environmental monitoring. He is passionate about developing affordable and efficient technological solutions, particularly the use of mobile LiDAR and AI-driven tools for soil disturbance estimation and posture evaluation in forest labor. His interdisciplinary approach merges forestry, computer science, and ergonomics, contributing to sustainable and safe forestry practices. Through these interests, he aims to bridge the gap between traditional forestry operations and modern intelligent systems.

Award

Gabriel’s academic and professional contributions have been recognized through several prestigious scholarships and awards. He has twice secured first place in the “My Bachelor/Dissertation Project” competitions held in 2022 and 2023, scoring nearly perfect marks. In 2022, he received the “Premiul special pentru studenti straini” award at the Premiul AFCO. He has also been a recipient of multiple scholarships, including the Transilvania Academica Scholarship, UNITBV Ph.D. Scholarship for International Graduates, and funding from “Proiectul Meu de Diploma” programs. Earlier in his career, he was awarded performance scholarships by the Government of Ghana and Poku Transport Ghana for his outstanding performance in forest sciences.

Publication

Gabriel has authored several notable publications that demonstrate his expertise in forest operations and technological innovation. His key works include:

Forkuo, G.O., & Borz, S.A. (2023). Accuracy and inter-cloud precision of low-cost mobile LiDAR technology in estimating soil disturbance in forest operations. Frontiers in Forests and Global Change, 6. Cited in multiple studies on forest soil impact monitoring.

Forkuo, G.O. (2023). A systematic survey of conventional and new postural assessment methods. Revista Padurilor, 138(3), 1-34.

Borz, S.A., Morocho Toaza, J.M., Forkuo, G.O., Marcu, M.V. (2022). Potential of measure app in estimating log biometrics: a comparison with conventional log measurement. Forests, 13(7), 1028.

Borz, S.A., Forkuo, G.O., Oprea-Sorescu, O., & Proto, A.R. (2022). Development of a robust machine learning model to monitor the operational performance of sawing machines. Forests, 13(7), 1115.

Forkuo, G.O., Proto, A.R., & Borz, S.A. (2024). Feasibility of low-cost mobile LiDAR technology in estimating soil disturbance in forest operations. SSRN.

Forkuo, G.O. (1999). Post-fire tree regeneration studies in the Kumawu Water Supply Forest Reserve. B.Sc. Thesis, KNUST-Kumasi.

Presented paper at FORMEC 2023 in Florence, Italy, highlighting applications of mobile LiDAR in operational environments.

Conclusion

Gabriel Osei Forkuo exemplifies the intersection of academic rigor, practical expertise, and technological innovation in the field of forest operations. His work continues to advance the integration of smart technologies into sustainable forestry, driven by a deep commitment to both ecological preservation and worker safety. Through his research, publications, and leadership roles, Gabriel has built a profile of excellence, contributing significantly to forestry engineering and shaping the next generation of sustainable forest management solutions.

Ali Mehrizi | Machine Learning | Best Paper Award

Posted on by sciencefather

Dr. Ali Mehrizi | Machine Learning | Best Paper Award

Lecturer at Ferdowsi University of Mashhad, Iran.

Ali Mehrizi is a distinguished researcher and lecturer in Artificial Intelligence (AI) and Machine Learning at Ferdowsi University of Mashhad (FUM), Iran. With a wealth of experience exceeding a decade, his expertise spans adaptive probabilistic models, distributed learning, multi-target tracking, time series forecasting, and Gaussian Mixture Probability Hypothesis Density (GMPHD) methods. Dr. Mehrizi has published multiple impactful articles in renowned journals such as Expert Systems with Applications and Fuzzy Sets and Systems. He is deeply committed to advancing the understanding and application of AI techniques and has successfully mentored numerous students in areas ranging from Data Mining to Advanced Operating Systems.

Profile

Google Scholar

Education

Dr. Mehrizi educational background is rooted in Artificial Intelligence. He is currently pursuing a Ph.D. in AI at Ferdowsi University of Mashhad (2017–2024), under the supervision of Professor H. Sadoghi Yazdi. His dissertation focuses on financial time series forecasting using experience-based adaptive learning, a project that has already produced several publications in top-tier journals. Previously, he earned an M.Sc. in AI from Azad University of Mashhad (2011–2013), where he worked on adaptive semi-supervised learning, optimizing self-organizing map models. His early academic journey began with a B.Sc. in Computer Engineering from the University of Birjand, later transferring to Azad University of Mashhad.

Experience

Dr. Mehrizi professional career spans various roles, beginning in 2001 when he became the IT & Network Manager at the Faculty of Engineering. In this capacity, he significantly improved the system performance and network management. Since 2011, he has been involved in research in AI and Machine Learning, contributing to the development of machine learning models and publishing his findings in high-impact journals. He has also served as a lecturer since 2013, teaching a variety of undergraduate and graduate courses, including Data Mining, Operating Systems, and Advanced Operating Systems. As a researcher, he has mentored students in their theses, particularly in machine learning and pattern recognition, fostering the next generation of AI experts.

Research Interests

Dr. Mehrizi  research interests are broad, focusing on several key areas within the domain of AI. His work on distributed adaptive learning, particularly through Diffusion LMS and Diffusion RLS, aims to optimize decentralized data processing for dynamic systems. In addition, he has contributed to probabilistic and hypothesis-based learning, exploring the use of Gaussian Mixture Probability Hypothesis Density (GMPHD) models for uncertainty-based learning and tracking. His research also delves into time series analysis and forecasting, with a particular focus on financial markets. Dr. Mehrizi’s interest in multi-target tracking extends to real-time tracking algorithms, emphasizing performance in noisy and incomplete data environments. He is also committed to semi-supervised learning, exploring hybrid methods that bridge supervised and unsupervised learning approaches in scenarios with limited labeled data.

Awards

Dr. Mehrizi contributions to the fields of AI and machine learning have earned him recognition in various academic and professional circles. He has been nominated for multiple awards for his research, particularly in adaptive learning and time series forecasting. His work is highly regarded in the academic community, and he continues to push the boundaries of AI research, especially in the areas of distributed learning and multi-target tracking.

Publications

Dr. Mehrizi has authored several articles in well-respected journals in AI and machine learning. His key publications include:

Mehrizi, A., & Yazdi, H. S. (2019). “Adaptive probabilistic methods for long-term financial time series forecasting.” Expert Systems with Applications.

Mehrizi, A., & Yazdi, H. S. (2020). “Semi-supervised learning using GSOM for adaptive classification.” Fuzzy Sets and Systems.

Mehrizi, A. (2022). “Distributed adaptive learning for dynamic systems using Diffusion LMS and RLS.” Emerging Markets Finance and Trade.

Mehrizi, A., & Yazdi, H. S. (2021). “Gaussian Mixture Probability Hypothesis Density for multi-target tracking.” Journal of Machine Learning Research.

These publications have been cited extensively by various researchers in the fields of machine learning, AI, and financial forecasting, underscoring Dr. Mehrizi’s significant impact on the academic community.

Conclusion

Dr. Ali Mehrizi is a leading researcher and educator in the field of Artificial Intelligence and Machine Learning, with a deep commitment to advancing these fields through his innovative research. His extensive academic background and his practical experience in both teaching and real-world applications have made him an invaluable asset to Ferdowsi University of Mashhad. With a strong focus on adaptive learning, probabilistic models, and time series forecasting, Dr. Mehrizi continues to contribute to the evolution of AI. His work not only shapes academic research but also provides vital insights into practical AI solutions for industries like finance and engineering. As a mentor and educator, he remains dedicated to shaping the future of AI professionals and researchers.

Mohsen Saroughi | Machine Learning | Best Scholar Award

Posted on by sciencefather

Mr. Mohsen Saroughi | Machine Learning | Best Scholar Award

Researcher | university of tehran | Iran

Mohsen Saroughi is an accomplished water resource management professional with a passion for research and innovation. With expertise in machine learning, groundwater modeling, and hydrology, Mohsen has established himself as a leading figure in applying artificial intelligence and optimization techniques to water resource challenges.

Profile

Google scholar

Education 🎓

  • Master’s in Water Resource Management (2018–2021): University of Tehran, Tehran, Iran (CGPA: 3.5/4)
  • Bachelor’s in Water Engineering (2014–2018): University of Bu-Ali Sina, Hamedan, Iran (CGPA: 3.1/4)

Experience 💼

Mohsen has served as a teaching assistant and research mentor, guiding students on projects in hydrology and groundwater management. His professional experience includes roles as a language editor, GIS consultant, and intern, where he demonstrated expertise in modeling, remote sensing, and IT solutions.

Research Interests 🔬

Mohsen’s research spans groundwater management, machine learning, climate change, and systems dynamics. He excels in applying artificial intelligence to water resource optimization and hydrological modeling.

Publications 📚

“A novel hybrid algorithms for groundwater level prediction”

  • Authors: M Saroughi, E Mirzania, DK Vishwakarma, S Nivesh, KC Panda, …
  • Journal: Iranian Journal of Science and Technology, Transactions of Civil Engineering
  • Year: 2023
  • Citations: 31

“Hybrid COOT-ANN: a novel optimization algorithm for prediction of daily crop reference evapotranspiration in Australia”

  • Authors: E Mirzania, MH Kashani, G Golmohammadi, OR Ibrahim, M Saroughi
  • Journal: Theoretical and Applied Climatology 154 (1), 201-218
  • Year: 2023
  • Citations: 7

“Shannon entropy of performance metrics to choose the best novel hybrid algorithm to predict groundwater level (case study: Tabriz plain, Iran)”

  • Authors: M Saroughi, E Mirzania, M Achite, OM Katipoğlu, M Ehteram
  • Journal: Environmental Monitoring and Assessment 196 (3), 227
  • Year: 2024
  • Citations: 5

“Prediction of monthly groundwater level using a new hybrid intelligent approach in the Tabriz plain, Iran”

  • Authors: E Mirzania, M Achite, N Elshaboury, OM Katipoğlu, M Saroughi
  • Journal: Neural Computing and Applications, 1-16
  • Year: 2024
  • Citations: 1

“Evaluate effect of 126 pre-processing methods on various artificial intelligence models accuracy versus normal mode to predict groundwater level (case study: Hamedan-Bahar …”

  • Authors: M Saroughi, E Mirzania, M Achite, OM Katipoğlu, N Al-Ansari, …
  • Journal: Heliyon 10 (7)
  • Year: 2024
  • Citations: 0

Awards 🏆

  • Ranked 1% in Official Judicial Experts Water Exam (2024)
  • 6th in Iranian University Entrance Master Exam (2018)
  • 2nd in Provincial Chemistry Competition (2012)

Conclusion 🌍

Mohsen Saroughi is a highly competent and accomplished researcher with strengths in advanced modeling, machine learning applications, and groundwater management. His technical expertise, leadership in mentoring students, and significant contributions to both academic literature and practical tools position him as a strong candidate for the Best Researcher Award. To further enhance his impact, expanding his international collaborations and engaging in projects that directly affect societal challenges could bolster his already impressive academic and professional trajectory.