Find Academic Supervisors

Sasu TarkomaView profile

Professor

• Computer Science
• Artificial Intelligence
• Machine Learning
• +5 more

Sasu Tarkoma is a Professor and Acting Dean at the Faculty of Science , University of Helsinki, with affiliations to the Helsinki Institute of Sustainability Science and Helsinki Institute of Urban and Regional Studies . His research focuses on Computer Science , particularly in Artificial Intelligence , Internet of Things , and 5G/6G networks . Education : PhD in Computer Science (University of Helsinki) Academic Roles : Supervisor for Doctoral Programme in Computer Science, Docent in Department of Computer Science Research Interests span AI-driven network optimization, edge computing for 5G/6G, digital twinning, and IoT-based environmental monitoring. His work addresses challenges in federated learning , low-cost sensing , and autonomous drone deployments . Supervision and Projects : Supervised numerous Master's and PhD students, including Pengfeng Su and Peifeng Su. Leads projects like BF AgentFormers (AI for platform stability) and NordForsk - Tarkoma (2024-2028) focusing on 6G data-driven systems. Scientific Awards : Recipient of The best textbook of 2009 prize Collaborations include partnerships with institutions in Finland and international actors like ACM and IEEE, with activities in conferences and peer review (e.g., ACM DEBS 2025).

Indrė ŽliobaitėView profile

Professor

• Data Science
• Machine Learning
• Life Science Informatics
• +3 more

Indrė Žliobaitė is a Professor at the Department of Computer Science, Faculty of Science, University of Helsinki, and holds a Docent title in the same department. She maintains dual affiliations with the Department of Geosciences and Geography and serves as supervisor for both the Doctoral Programme in Geosciences and Doctoral Programme in Computer Science. Her research integrates data science and machine learning with earth sciences, focusing on evolutionary paleontology, macroecology, and macroevolution. She develops computational frameworks for analyzing fossil records, modeling species longevity, and reconstructing paleoenvironments, with specific applications in habitat suitability prediction and ecometric inference. Her work bridges algorithmic innovation with paleontological data interpretation. Recent publications reveal a cohesive trajectory where machine learning techniques—particularly probabilistic modeling and Bayesian approaches—are systematically applied to paleontological questions. This includes modeling fossil mammal community dynamics, inferring historical climate impacts on species distribution, and establishing quantitative laws for macroevolutionary processes, demonstrating how computational methods can unlock patterns in deep-time ecological data. Žliobaitė actively supervises doctoral candidates through two university programmes and leads the Academy of Finland project "Macroevolution of ecological relationships" (2023-2027). She collaborates internationally with the Turkana Basin Institute, Staatliches Museum Naturkunde Stuttgart, and Institut Catala de Paleontologia, and manages the New and Old Worlds Mammal Fossil Database (NOW), a critical infrastructure for paleontological research.

Petri PellikkaView profile

Professor

• Remote Sensing
• Geosciences
• Environmental Sciences
• +5 more

Petri Pellikka serves as Professor at the Department of Geosciences and Geography, University of Helsinki, and holds adjunct positions at University of Nairobi (Wangari Maathai Institute of Peace and Environmental Studies) and University of Turku, along with visiting professorship at Wuhan University. He is affiliated with the Helsinki Institute of Sustainability Science (HELSUS) and supervises doctoral programs in Atmospheric Sciences, Geosciences, and Interdisciplinary Environmental Sciences. His research spans remote sensing, environmental sciences, and African ecosystems with focus on land use change, biodiversity conservation, and climate-smart agriculture. Key interests include geospatial analysis of human-wildlife conflicts, invasive species monitoring, urban phenology, and sustainable agricultural practices in East Africa. His work integrates field data with satellite remote sensing and machine learning techniques to address environmental challenges. Pellikka's scientific contributions include 326 research outputs and 27 projects, with recent publications analyzing elephant conservation strategies in Kenya, Prosopis invasion detection, and urban land surface phenology. His work demonstrates strong international collaboration, particularly with African institutions. Suomalaisen Tiedeakatemian jäsenyys (Finnish Academy of Science Membership, 2010) He has supervised 14 theses and participates extensively in academic service including editorial work for International Journal of Applied Earth Observation and Geoinformation, peer review, and research council activities. His projects include REACT (Climate-smart agricultural systems in East Africa) and Taita Research Station development, focusing on field laboratories for environmental monitoring in Kenyan ecosystems.

Naser Hossein MotlaghView profile

Academic

• Internet of Things (IoT)
• Wireless Sensor Networks (WSN)
• Environmental Sensing
• +6 more

Naser Hossein Motlagh is an Academy Research Fellow at the Department of Computer Science, University of Helsinki, affiliated with the Helsinki Institute of Sustainability Science (HELSUS) and Helsinki Institute of Urban and Regional Studies (Urbaria). He is an IEEE Senior Member and ACM Professional Member with a D.Sc. in Networking Technology from Aalto University (2018). Education: D.Sc. (Aalto University), M.Sc. & B.Sc. (University of Vaasa) His research focuses on Internet of Things (IoT) , Wireless Sensor Networks , and Environmental Sensing for smart cities and sustainability. Key projects include drone-based air quality monitoring, underwater plastic detection systems, and edge computing architectures for smart environments. Recent publications highlight trends in low-cost sensor networks for urban pollution, AI-driven adaptive systems , and quantum computing integration with IoT. He chairs the annual EnvSys workshop and organizes the IEEE World Congress on Services. Scientific Awards: Academy Research Fellow (Research Council of Finland, 2024–2028) IEEE Senior Member ACM Professional Member He supervises Master’s and Licentiate theses and contributes to teaching networking technologies at the University of Helsinki. His work spans collaborations with institutions like Tokyo Institute of Technology and TU Wien.

• Generative Models
• Computer Science
• Machine Learning
• +3 more

Tuomas Kynkäänniemi is a Doctoral Researcher at the School of Science's Department of Computer Science, affiliated with Professor Jaakko Lehtinen's professorship. His research focuses on generative models, diffusion models, and evaluation metrics for machine learning systems. He has contributed to advancements in image generation, algorithm optimization, and feature space analysis. Education highlights include an MSc Thesis awarded the prestigious 'Best MSc Thesis Award' in 2020. His work bridges theoretical computer science with practical applications in image processing and time-series analysis. Key research areas include disentangling cyclic/random effects in time-lapse sequences, improving diffusion model performance through novel guidance techniques, and evaluating generative models using metrics like Fréchet Inception Distance. Collaborations span academic institutions, with recent work appearing in top conferences like NeurIPS and ICLR. Award-winning contributions include pioneering studies on ImageNet class impacts on evaluation metrics and scalable training methods for StyleGAN2. His research emphasizes both foundational machine learning theory and real-world applicability in domains like planetary science and environmental monitoring.

Wenshuai ZhaoView profile

Researcher

• Multi-Agent Reinforcement Learning
• Humanoid Robotics
• Reinforcement Learning
• +4 more

Wenshuai Zhao is a Doctoral Student in the School of Electrical Engineering and a Postdoctoral Researcher in the Department of Computer Science. His research focuses on Multi-Agent Reinforcement Learning, Humanoid Robotics, and Temporal Consistency in Deep Learning. Master of Engineering and Technology, Fudan University (2020) Master of Natural Sciences, University of Turku (2020) His work spans dynamic models, sample efficiency, and policy optimization. Recent publications include AgentMixer (2025) for policy factorization, Bi-Level Motion Imitation (2025) for humanoid robots, and Optimistic Policy Gradient (2024) for multi-agent coordination. Collaborations include the EU's Recovery and Resilience Facility and Business Finland projects.

• Computational Imaging
• Compressed Sensing
• Signal Processing
• +5 more

Dr. Karen Eguiazarian is a Professor of Signal Processing at the Department of Computing Sciences , Tampere University . He leads the Computational Imaging research group and has served as head of the Signal Processing Research Community (SPRC) at Tampere University of Technology (2016-2018). Education: M.Sc. in Mathematics, Yerevan State University, Armenia (1981) Ph.D. in Physics and Mathematics, Moscow State University, Russia (1986) Doctor of Technology in Signal Processing, Tampere University of Technology, Finland (1994) His research focuses on Computational Imaging , Compressed Sensing , and Efficient Signal Processing Algorithms , with significant contributions to Image/Video Restoration and Compression . Recent work includes AI-driven phase imaging, hyperspectral reconstruction, and noise-robust algorithms for remote sensing and biomedical applications. Scientific Awards: Service Award from the Society for Imaging Science and Technology (IS&T) (2014) Honorary Doctoral Degree from Don State-Technical University, Russia (2015) Dr. Eguiazarian has supervised 25 doctoral theses and published over 650 papers. He serves as Editor-in-Chief of the Journal of Electronic Imaging and associate editor of the IEEE Transactions on Image Processing , while co-founding Noiseless Imaging Oy , a Tampere University spin-off.

• Computer Science
• Neuroscience
• Medical Imaging
• +3 more

Fengyu Cong is a Visiting Professor at the Faculty of Information Technology of the University of Jyväskylä (Finland). His research focuses on interdisciplinary computational neuroscience, biomedical signal processing, and machine learning applications in healthcare. Key contributions include EEG/fMRI analysis for mental health disorders such as depression and autism spectrum disorder, as well as federated learning methods for privacy-sensitive medical data. He has presented at major conferences including the 6th Conference on Mismatch Negativity (2012) and ESCAN 2014 , showcasing work on preattentive facial expression processing in neurological populations. His affiliations include the Engineering and Secure Communications Engineering and Signal Processing groups within his faculty. Research interests span neural signal analysis, multimodal imaging techniques, and AI-driven diagnostics. Notable methodologies include tensor decomposition for fMRI preprocessing, HMM-based sleep stage classification, and federated learning frameworks for distributed healthcare applications. His work bridges computer science and clinical neurology, with publications in top-tier journals addressing topics like vascular cognitive impairment, neural oscillations in autism, and artifact removal in biomedical signals.

Martha Arbayani ZaidanView profile

Adjunct Professor

• Environmental Sensing
• Air Quality Monitoring
• Atmospheric Science
• +4 more

Dr. Martha Arbayani Zaidan serves as an Academy Research Fellow at the University of Helsinki's Department of Computer Science and holds the prestigious Docent title (equivalent to Adjunct Professor) at the Institute for Atmospheric and Earth System Research (INAR) and Helsinki Institute of Sustainability Science (HELSUS). Her interdisciplinary work bridges computer science, atmospheric physics, and sustainability science to advance environmental sensing technologies. Her educational foundation includes a PhD in Automatic Control and Systems Engineering from the University of Sheffield (2014), where she developed Bayesian approaches for complex system prognostics, complemented by an MSc in Control Systems (2009) and BEng in Electrical Engineering (2007). Dr. Zaidan's research focuses on environmental sensing systems , particularly drone-based air quality monitoring and machine learning applications for atmospheric data analysis. She investigates critical phenomena including black carbon distribution in Asian megaregions, urban-suburban air quality disparities in East Africa, and aerosol size distribution modeling. Her work emphasizes practical applications for sustainability challenges through advanced computational methods. Her scientific contributions have earned significant recognition, including the competitive Academy Research Fellowship from Finland's Academy of Finland (2023) and the HIIT Research Fellowship (2022), reflecting her leadership in environmental AI research. As an active research leader, Dr. Zaidan directs the Academy of Finland project on AI-enhanced sensing technologies and participates in the large-scale InterEarth RESET initiative. She co-founded the annual EnvSys workshop series, fostering international collaboration in environmental sensing for smart cities. Her supervision record includes mentoring graduate students in computational environmental science.

• Energy Systems
• Smart Grids
• Demand Response
• +3 more

Mikko Nykyri is a Post-doctoral researcher at the Department of Electrical Engineering within the School of Energy Systems at Lappeenranta-Lahti University of Technology (LUT). His research focuses on energy systems with particular emphasis on smart grids, energy communities, and demand response mechanisms. His work bridges theoretical approaches with practical applications in the energy sector, aligning with LUT's strategic focus on energy transition. Dr. Nykyri's research interests center around the intersection of energy systems and digital technologies. He investigates how machine learning, particularly deep reinforcement learning, can optimize energy efficiency in buildings and industrial processes. His work on energy communities explores economic models, blockchain-based settlement systems, and educational approaches through serious games. He also maintains research interests in power electronics, including inverter technologies and semiconductor device characterization. His research demonstrates strong interdisciplinary connections across electrical engineering, computer science, and energy economics. An analysis of Dr. Nykyri's publication history reveals a clear evolution from fundamental power electronics research toward increasingly complex system-level applications. His early work focused on specific technical challenges in power conversion and semiconductor devices, while his recent publications address holistic energy system challenges including community-scale economics, AI-driven optimization, and educational frameworks. This progression reflects the broader energy transition from component-level improvements to integrated system solutions, with particular emphasis on the role of digitalization in enabling new energy paradigms. Dr. Nykyri has established a robust collaborative network, frequently working with researchers including Tommi J. Kärkkäinen, Saku Levikari, and Pertti Silventoinen. His peer review activity for Applied Energy demonstrates his recognized expertise in the field. His research maintains a practical orientation, with multiple studies involving real-world industrial applications and educational demonstrators that bridge academic research with industry implementation needs.