Find Academic Supervisors

Panagiotis TraganitisView profile

Assistant Professor

• Statistical Signal Processing
• Machine Learning
• Crowdsourcing
• +4 more

Panagiotis Traganitis is an Assistant Professor in the Electrical and Computer Engineering (ECE) Department at Michigan State University (MSU), where he joined in August 2022. Previously, he was a Postdoctoral Researcher at the University of Minnesota’s Signal Processing in Networking and Communications (SPiNCOM) group under Prof. Georgios B. Giannakis. His research focuses on statistical signal processing, machine learning, crowdsourcing, weak supervision, and network science, with applications in big data analytics and distributed learning. Education: Ph.D. in Electrical Engineering, University of Minnesota (2019), Thesis: Scalable and Ensemble Learning for Big Data M.Sc. in Electrical Engineering, University of Minnesota (2015), Thesis: Large-scale Clustering using Random Sketching and Validation Diploma in Electrical & Computer Engineering, National Technical University of Athens (2013), Thesis: Reinforcement Learning Methods for Cognitive Radio Networks Research Interests: His work spans statistical learning, blind ensemble methods, weak supervision, subspace clustering, and graph-based algorithms. Current projects include blind ensemble learning, adversarial detection in crowdsourcing, and self-supervised learning. Awards & Honors: Gerondelis Foundation Graduate Scholarship (2015) Finalist, CAMSAP 2017 Student Paper Award Eurobank’s Award of Excellence in Greek Nationwide University Entrance Exams (2007) Teaching & Mentorship: He has served as a teaching assistant for courses on statistical methods and nonlinear optimization at the University of Minnesota. He is currently seeking motivated Ph.D. students to join his research group. His lab focuses on advancing robust, scalable learning algorithms with real-world applications. Labs & Collaborations: Active member of the SPiNCOM research group, collaborating on projects related to signal processing, machine learning, and network science.

• Machine Learning
• Nanotechnology Sensors
• Bayesian Inversion
• +3 more

Amirreza Khodadadian is a researcher affiliated with TU Wien's E194-06 Machine Learning Research Group. His work focuses on computational methods for nanosensors, numerical solutions to stochastic partial differential equations, and Bayesian inversion techniques. He collaborates extensively with Prof. Clemens Heitzinger and other researchers in fields like nanotechnology and applied mathematics. Key research areas include meshless numerical methods (e.g., interpolating element free Galerkin), optimal multi-level Monte Carlo algorithms, and sensor modeling using machine learning and Bayesian approaches. His publications address challenges in nanoelectronics, groundwater contamination modeling, and phase-field fracture simulations. Khodadadian's contributions span theoretical developments and practical applications, including work on carbon nanotube field-effect transistors and hyper-parameter optimization for autoencoder-based systems. He actively participates in projects funded by the Austrian Science Fund (FWF) and collaborates across disciplines to advance computational sensor technology.

Paul ConstableView profile

Senior Lecturer

• Retinal Biomarkers
• Neurodevelopmental Disorders
• Signal Analysis
• +3 more

Paul Constable is a Senior Lecturer at the College of Nursing and Health Sciences and a Full Member of the Caring Futures Institute. His research focuses on identifying retinal biomarkers for neurodevelopmental disorders using machine learning and signal analysis. He leads the retinalbiomarkers group, collaborating internationally with teams in the UK, Germany, Brazil, and the US. His expertise includes visual electrophysiology (ERG/EOG), deep learning frameworks (TensorFlow, PyTorch), and portable ERG device development to enhance accessibility. Education: Postgraduate Certificate in Ocular Therapeutics (Australian College of Optometry, 2020) PhD in Optometry (City University of London, 2007) Bachelor of Science in Optometry (University of Melbourne, 1991) Awards: Marmor Award for Clinical Innovation in Electrophysiology (2014) Vice President & Executive Dean’s Award (2019) Research Interests: Retinal biomarker discovery for autism spectrum disorder and ADHD Signal analysis (Wavelet transforms, Bayesian modeling) Machine learning applications in ophthalmology His work contributes to UN Sustainable Development Goals related to education and health. Recent studies include spectral analysis of ERGs for neurodevelopmental disorders and AI-driven synthetic signal generation to improve biomarker classification.

• Wireless Communications
• Networking
• Signal Processing
• +3 more

Sneha Kasera is a Researcher at the University of Utah's Department of Computer Science, affiliated with the University of Utah. Her work focuses on wireless communications, networking, and signal processing, with an emphasis on spectrum management, machine learning applications in networks, and security. She has contributed extensively to projects like the POWDER platform for wireless experimentation and spectrum analysis. Her research interests include developing advanced techniques for spectrum monitoring, dynamic radio resource allocation, and leveraging machine learning for network optimization. Key projects include Radio Dynamic Zones (RDZ) for efficient spectrum utilization and Bayesian learning methods for heatmap construction in outdoor wireless environments. Her recent work explores multi-agent reinforcement learning for mmWave power allocation, adversarial attacks on localization systems, and privacy-preserving exposure notification via hash collision techniques. She has also pioneered methods for crowdsourced spectrum monitoring and calibration-free full-duplex systems. Collaborations include contributions to the POWDER platform, which enables scalable wireless research. Her technical expertise spans hardware-software integration, network security, and algorithm design for 5G/6G systems.

Zhanglong CaoView profile

Research Fellow

• Statistical Modelling
• Bayesian Inference
• Agricultural Spatial Analysis
• +3 more

Dr. Zhanglong Cao is a Research Fellow at Curtin University's Centre for Crop Disease Management (CCDM), affiliated with the School of Molecular and Life Sciences and the Faculty of Science and Engineering. His research focuses on statistical modeling, Bayesian inference, and computational biology, particularly applied to agricultural challenges such as crop disease management and fungicide resistance. He collaborates on GRDC projects to enhance on-farm trial design and spatial analysis. Research Interests: Statistical Modelling & Bayesian Methods Agricultural Spatial Analysis & Crop Disease Management Computational Biology & Data Science Fungicide Resistance Economics Recent work emphasizes optimizing on-farm experiments, socio-economic impacts of crop diseases, and adaptive algorithms for trajectory reconstruction. His studies bridge statistical innovation with real-world agricultural problems, including wheat and chickpea disease mitigation strategies. Awards: None explicitly listed in available records. Lab Affiliation: Centre for Crop Disease Management (CCDM), Curtin University.

• Smart Grid Security
• Privacy-Preserving Techniques
• Federated Learning
• +5 more

Mohamed I. Ibrahem is an active academic researcher specializing in cybersecurity applications for smart grid infrastructure and Internet of Things systems. His work bridges computer science, electrical engineering, and artificial intelligence with a particular focus on privacy-preserving techniques and secure machine learning applications. Dr. Ibrahem's research interests center on smart grid security , where he has developed innovative approaches for electricity theft detection, false data injection prevention, and privacy-preserving monitoring systems. His work in federated learning security addresses critical vulnerabilities in distributed machine learning systems, particularly against Trojan attacks and evasion techniques. Additional research areas include explainable AI applications in healthcare diagnostics, IoT security mechanisms, and deep learning optimization for resource-constrained environments. His recent publication trends reveal a growing emphasis on practical security implementations for real-world energy infrastructure, with increasing attention to explainability and robustness in AI-driven security systems. The interdisciplinary nature of his work connects cybersecurity principles with specific domain challenges in power systems and healthcare applications. Dr. Ibrahem has secured research funding for multiple projects focused on smart grid protection systems and privacy-preserving machine learning frameworks, though specific grant details are not visible in the publication metadata. His collaborative research network spans multiple international institutions with strong connections to Middle Eastern universities.

• Simultaneous Localization and Mapping
• Millimeter Wave Engineering
• Received Signal Strength
• +3 more

Ossi Kaltiokallio is a Senior Research Fellow in Electrical Engineering, specializing in cutting-edge research at the intersection of robotics, wireless communications, and signal processing. His work primarily focuses on Simultaneous Localization and Mapping (SLAM) , millimeter-wave technology, and device-free localization frameworks. Collaborations with leading researchers across institutions highlight his contributions to advancing wireless sensing methodologies. Expertise in SLAM algorithms and bistatic radio applications Pioneering research in double-bounce signal utilization for obstructed environments Recipient of the prestigious Jean-Pierre Le Cadre Award (2021) His recent publications in IEEE Transactions on Robotics and EuCAP conferences demonstrate innovative approaches to multi-hypotheses filtering, graph-based optimization, and Gaussian process modeling. These works align with advancements in wireless sensing for robotics and IoT applications. 2025: Key contributions to batch SLAM frameworks and bistatic mapping techniques 2024: Development of multi-hypotheses importance densities and double-bounce signal analysis in mmWave systems Ossi's research also extends to creating open datasets for 60 GHz indoor sensing, ensuring reproducibility and community-driven progress in wireless localization technologies. Scientific Awards Jean-Pierre Le Cadre Award (2021) - Recognized for excellence in radio SLAM research

Maria ChizhovaView profile

Assistant Professor

• Digital Heritage Technologies
• 3D Reconstruction
• Photogrammetry
• +5 more

Maria Chizhova is an Assistant Professor in Digital Technologies in Heritage Conservation at the University of Bamberg's Centre for Heritage Conservation Studies and Technologies (KDWT). She holds a Dr.-Ing. degree from Technical University of Munich and has a Dipl. Eng. in Surveying from State Academy of Agriculture in Ivanovo. Doctorate: 2014-2019, Technical University of Munich (Civil, Geo and Environmental Engineering) Diploma: 2006-2011, State Agricultural Academy in Ivanovo Her research focuses on 3D digitalization, photogrammetry, laser scanning, and AI applications for heritage conservation. Key projects include VRScan3D (virtual laser scanner simulator), GeoRek (geodetic methods in Ukraine), and VirScan3D (3D reconstruction of historical objects). She has developed automated systems for timber structure analysis and orthodoxy church reconstruction. Recent publications show expertise in 3D simulation , point cloud segmentation , and multi-sensor integration . She has held research fellowships at Technical University of Warsaw, Fondazione Bruno Kessler (Italy), Carleton University (Canada), and Michigan Tech University (USA). DAAD-funded VRScan3D project (2019-2021) Research on Jewish cemeteries in Franconia Developed methodologies for historic timber analysis Her work combines machine learning , Bayesian networks , and cellular automata for heritage documentation, with applications in digital twins and mixed reality environments.

Andreas GiengerView profile

Research Fellow

• Construction Robotics
• Data-based Modeling
• Fault Detection and Diagnosis
• +3 more

Dr. Andreas Gienger is a Junior Research Group Leader and Group Leader for Construction Robotics at the Institute for System Dynamics, University of Stuttgart, affiliated with the Cluster of Excellence IntCDC. He holds a Dr.-Ing. (Doctor of Engineering) degree and leads research in construction robotics, automation, and adaptive structures. Education: Master's in Technical Cybernetics, University of Stuttgart (2013–2016) Bachelor's in Mechanical Engineering, University of Stuttgart (2010–2013) Research Interests: His work focuses on data-driven approaches for robotics and structural systems, including fault diagnosis, optimization of large-scale manipulators, and cooperative control strategies. Key themes include adaptive structures, sensor integration, and real-time automation in construction. Publications: Recent articles (2020–2023) emphasize robotics applications in construction, fault-tolerant control, and data-based modeling. Trends include the integration of machine learning (CNNs, Bayesian methods) with traditional control systems for adaptive structures and industrial automation. Awards: None listed. Teaching: Courses include Trajectory Generation, Numerical Optimization, Simulation Technology, and Smart Manufacturing. He supervises projects in automation and process engineering. Labs/Teams: Leads the Construction Robotics group at the Institute for System Dynamics, collaborating on projects like the SFB1244 (adaptive structures) and IntCDC cluster.

Andrey A. PopovView profile

Assistant Professor

• Computational Science
• Data Assimilation
• Bayesian Inverse Problems
• +8 more

Andrey A. Popov is an Assistant Professor in the Department of Information and Computer Sciences at the University of Hawaiʻi at Mānoa, part of the College of Natural Sciences. His research lies at the intersection of computational science, data assimilation, uncertainty quantification, and machine learning, with applications to dynamical systems and aerospace navigation. His research interests include computational science, Bayesian inverse problems, data assimilation, uncertainty quantification, theory-guided machine learning, reduced order modeling, and ensemble filtering. He develops methods that bridge theoretical rigor with practical applicability, aiming for solutions no more than one step away from real-world implementation. His work often integrates machine learning with physical models to improve state estimation and prediction in complex systems. The recent publications (2023–2024) reflect a strong trend in advancing ensemble-based filtering techniques—particularly ensemble Kalman and particle filters—with innovations in covariance adaptation, weight optimization, and non-Gaussian modeling. There is also a growing emphasis on multifidelity and reduced-order modeling, especially using autoencoders and neural networks to handle small data regimes in chaotic systems. Applications span geophysics, aerospace (e.g., Mars entry navigation), and cislunar tracking, demonstrating interdisciplinary impact. Scientific Awards: Jean-Pierre Le Cadre Best Paper Award at FUSION 2024 Dr. Popov actively mentors students and welcomes prospective graduate students to contact him via email or during office hours. While specific grant details are not provided, his publication output and conference presence suggest active external funding. He teaches courses such as ICS 141 and emphasizes algorithmic and mathematical foundations in computing. He is involved in collaborative research with institutions like the Oden Institute and researchers including Adrian Sandu and Renato Zanetti, focusing on advanced filtering and data assimilation techniques. His group likely engages in methodological development for state estimation in high-dimensional, nonlinear systems.

Andrea FacchinettiView profile

Assistant Professor

• Bioengineering
• Continuous Glucose Monitoring
• Diabetes Technology
• +3 more

Andrea Facchinetti is an Assistant Professor in Bioengineering at the Department of Information Engineering, University of Padova, Italy. His research focuses on developing advanced algorithms for continuous glucose monitoring systems and diabetes management technologies, with significant contributions to both academic research and commercial applications through technology transfer to Dexcom Inc. Dr. Facchinetti received his Laurea Quinquennale (summa cum laude) in Information Engineering from the University of Padova in 2005, followed by a Ph.D. in Bioengineering from the same institution in 2009. After serving as a Postdoctoral Fellow from 2009 to 2014, he was appointed Assistant Professor in 2014. His primary research interests center around processing data from continuous glucose monitoring (CGM) sensors, with specific focus on: Algorithms for signal denoising using Kalman filters and Bayesian smoothing techniques Strategies to reduce or eliminate calibrations in CGM sensors Real-time detection of hypo/hyperglycemic events using neural networks and statistical approaches Modeling of CGM data error and transient faults Development of type 1 diabetes simulators for testing decision-making systems Retrospective retrofitting methods to improve glucose concentration profiles Analysis of Dr. Facchinetti's recent publications (2023-2025) reveals an expanding research scope beyond traditional diabetes management. His work now encompasses post-bariatric hypoglycemia, neonatal glucose monitoring, integration of AI in clinical decision support systems, and applications of continuous glucose monitoring in novel populations including multiple sclerosis and amyotrophic lateral sclerosis patients. His research demonstrates a clear trajectory from foundational algorithm development toward practical clinical implementation and user-centered design of diabetes technologies. Dr. Facchinetti has been involved in significant technology transfer activities, with multiple patents optioned by and transferred to Dexcom Inc., a leading continuous glucose monitoring company. His work has contributed to commercial CGM systems including the Dexcom G4. He has co-authored over 70 international conference papers and numerous journal publications in high-impact diabetes and biomedical engineering journals. His research group maintains active collaborations with clinical partners and industry stakeholders to translate algorithmic innovations into practical diabetes management solutions. Current projects include developing decision support systems for pediatric type 1 diabetes, addressing post-bariatric hypoglycemia through forecasting algorithms, and creating modular platforms for real-world data acquisition in clinical trials.

James GrantView profile

Lecturer

• Bandit Learning
• Reinforcement Learning
• Online Sequential Decision Making
• +4 more

Dr. James Grant is a Lecturer in Statistics at Lancaster University's School of Mathematical Sciences since 2021, where he also serves as the EDI Lead for both the School and the ProbAI Research Hub. He is active in several roles at the Royal Statistical Society and serves as an Associate Editor for the ACM Transactions on Probabilistic Machine Learning. Grant completed his PhD in 2019 through the STOR-i Centre for Doctoral Training at Lancaster University under the supervision of Professors David Leslie, Kevin Glazebrook, and Roberto Szechtman. Prior to his PhD, he worked as a Machine Learning Research Student at Secondmind.ai and as a Research Associate within the STOR-i Centre for Doctoral Training. Dr. Grant's research focuses on online sequential decision making for problems with complex data structures, particularly in bandit learning and reinforcement learning. He specializes in multi-armed bandits, online optimization, and recommender systems where algorithms learn optimal decisions through iterative processes of decision-making, data observation, and model updating. His research emphasizes collaboration with industry, having worked on the Next-Generation Converged Digital Infrastructure project with BT. His publication record demonstrates strong expertise in bandit algorithms with applications spanning federated learning systems, anomaly detection in time series data, and phylogenetic tree analysis. Grant's work consistently bridges theoretical foundations with practical applications across telecommunications, surveillance systems, and decision-making frameworks. Notable Paper Award Winner at AISTATS 2020 for "On Thompson Sampling for Smoother-than-Lipschitz Bandits" Associate Editor for ACM Transactions on Probabilistic Machine Learning Active participant in Royal Statistical Society initiatives Dr. Grant currently supervises six PhD students working on diverse research topics including bandit learning, tropical statistics, anomaly detection, sequential simulation methods, safety in reinforcement learning, and Bayesian optimization. His former research associate, Changjiang He, has progressed to become a Lecturer in Computer Science at the University of Roehampton. As an EDI Lead, Grant actively promotes equality, diversity, and inclusion within the academic community while maintaining a robust research program that bridges theoretical statistics with real-world applications.

• Signal Processing
• Machine Learning
• Communication
• +3 more

Memduh KÖSE is a Lecturer in the Department of Electrical-Electronics Engineering at the Faculty of Engineering and Architecture, Kirsehir Ahi Evran University, Turkey. He has been working there since 2019 as a full-time faculty member after previously holding positions at Ahi Evran University's Computer Science Application and Research Center and Ankara University's Faculty of Engineering. His academic background includes: PhD in Electrical and Electronics Engineering from Ankara University (2019) Master's degree in Electrical and Electronics Engineering from Ankara University (2000) BSc in Electronics Engineering from Ankara University (1996) Dr. KÖSE's research spans multiple interdisciplinary areas at the intersection of signal processing, machine learning, and communication technologies. His work demonstrates a strong focus on practical applications of theoretical concepts, particularly in RF fingerprinting for wireless device identification and electronic nose systems for food quality assessment. He has made significant contributions to transient signal analysis, change point detection, and the application of machine learning techniques to solve real-world problems in food safety and wireless security. His research methodology often combines hardware implementation (frequently using Arduino platforms) with advanced data analysis techniques. His publication record shows a clear evolution from foundational work in signal processing and wireless communication toward increasingly applied research with direct industrial and consumer applications, particularly in food quality assessment systems. Recent publications (2024-2025) demonstrate a strong emphasis on machine learning applications for food safety, including electronic nose systems for chicken eggs, essential oils, stuffed mussels, and anchovies. Dr. KÖSE has successfully supervised five master's students, with thesis topics ranging from deep learning applications to security systems using facial recognition. He has been involved in seven research projects funded by higher education institutions and TÜBİTAK, focusing on Arduino-based sensor systems for food quality assessment, water quality monitoring, and IoT security. His teaching portfolio includes courses on probability and statistics, circuit analysis, and modeling and simulation methods, demonstrating both theoretical and practical expertise across the electrical and electronics engineering curriculum.

Piotr SzwedView profile

Lecturer

• Data Mining
• Software Engineering
• Computational Intelligence
• +5 more

Dr inż. Piotr Szwed is a Lecturer in the Department of Applied Computer Science at AGH University of Science and Technology, Kraków. He is affiliated with the Faculty of Electrical Engineering, Automatics, Computer Science and Biomedical Engineering (EAIiIB), where he teaches courses ranging from imperative and object-oriented programming to data exploration and computational intelligence. Research Interests: Data mining and knowledge discovery Fuzzy cognitive maps and their applications in transportation, risk assessment, and security Software engineering methodologies, including agile and ontology-driven development Intelligent transportation systems (ITS) and real-time traffic management Natural language processing for Polish texts, stylometry, and authorship attribution Ontology engineering, enterprise architecture verification, and model checking His work often bridges theoretical computer science with practical applications in urban mobility, safety systems, and enterprise software. Scientific Contributions: Pioneered the integration of fuzzy cognitive maps with evolutionary algorithms to predict traffic flows. Developed rule-based and machine-learning approaches to determine speed limits from geospatial data. Contributed to the INSIGMA intelligent transportation system aimed at enhancing urban mobility in Polish cities. Created formal verification techniques for ArchiMate business processes using NuSMV model checking. Advanced stylometric analysis for Polish texts, introducing part-of-speech features for authorship attribution. Teaching & Academic Service: Regularly teaches Programming (C, C++, Java), Software Engineering, Data Exploration, and Computational Intelligence. Supervises engineering and master theses in applied computer science. Maintains a public wiki with course materials, lab exercises, and consultation schedules for students. Utilizes Git-based repositories to streamline code submission and continuous assessment in laboratory classes. Laboratory & Facilities: He is located in building C-2, room 403, at AGH’s main campus, al. Mickiewicza 30, 30-059 Kraków. The lab supports courses that emphasize practical software development, version control, and collaborative project work.

• Signal Processing
• Ionospheric Physics
• Seismology
• +3 more

Assoc. Prof. Dr. Seçil Karatay is an Associate Professor at Kastamonu University's Faculty of Engineering and Architecture, Department of Electrical-Electronics Engineering. She holds a PhD in Physics from Fırat University (2010), an MSc in Physics (2005), and a BSc in Physics (2001). Her academic career spans roles including Department Head (2013-2017), Dean Assistant (2013-2016), and Director of Research Application Center (2016-2021). PhD: Physics, Fırat University, 2005-2010 MSc: Physics, Fırat University, 2002-2005 BSc: Physics, Fırat University, 1997-2001 Her research focuses on Signal Processing and Ionospheric Physics , particularly analyzing ionospheric disturbances related to seismic activity and space weather phenomena. She has pioneered algorithms like IONOLAB-FFT and Differential Rate of TEC (DROT) for detecting geophysical effects in ionospheric data. Her work spans machine learning applications for earthquake prediction, GPS-TEC analysis , and seasonal atmospheric variability studies. Recent publications highlight her expertise in 2023 Kahramanmaraş earthquakes ionospheric impact analysis, LSTM algorithm for disturbance classification, and Random Forest models for seismic precursor detection. With over 60 publications and citations exceeding 230, her research has significant SCI/SSCI indexing presence. Collaborations include Feza Arıkan (29 joint works), Ali Çınar (19), and Orhan Arıkan (14).