Find Academic Supervisors

Ricard GavaldàView profile

Professor

• Machine Learning
• Data Mining
• Healthcare Analytics
• +3 more

Ricard Gavaldà is a Professor in the Department of Computer Science at Universitat Politècnica de Catalunya (UPC), affiliated with the LARCA research group. Since February 2020, he has been on academic leave to work full-time at Amalfi Analytics, focusing on healthcare data analytics. His research interests include Machine Learning, Data Mining, and their applications to healthcare and social good. He has supervised numerous PhD students and contributed to impactful projects in clinical decision support, traffic prediction, and energy-efficient systems. Education details are not explicitly mentioned in the provided texts. His work spans data stream mining, algorithmic frameworks (e.g., MOA), and healthcare informatics. He has co-founded Amalfi Analytics to develop AI-driven solutions for healthcare management. Notable recent activities include co-chairing the Nectar Track at ECML PKDD 2025 and organizing workshops on Data Science for Social Good. Key technical contributions include methods for adaptive learning, probabilistic modeling, and interpretable AI systems. His research bridges theoretical foundations and real-world applications, with a focus on improving healthcare outcomes and sustainable practices.

• Knowledge Representation
• Answer Set Programming
• Non-monotonic Reasoning
• +5 more

Pedro Cabalar is Full Professor at the Department of Computer Science of the University of Corunna, Galicia, Spain, and current coordinator of the inter-university Master in Artificial Intelligence (Universities of A Coruña, Santiago de Compostela and Vigo). He also serves as Area Editor (Theory Foundations) for Theory and Practice of Logic Programming and as Standard Editor for the Artificial Intelligence journal. Education: PhD in Computer Science, University of Corunna, 2001 Master in Computer Science, Politéchnic University of Madrid, 1993 Bachelor in Computer Science (3-year degree), University of Santiago de Compostela / University of Corunna, 1989 Research interests revolve around Knowledge Representation & Reasoning , especially Answer Set Programming , non-monotonic reasoning , temporal and modal logics , and causal reasoning . He investigates theoretical foundations (equilibrium logic, temporal extensions, deontic operators) and practical systems (telingo, eclingo, aspBEEF), with applications ranging from planning and diagnosis to explainable AI and healthcare decision support. His recent articles (2023-2025) exhibit a clear trend toward temporal and metric extensions of ASP , explainability , and hybrid reasoning systems , often combining logic programming with deontic or probabilistic features. Scientific awards & recognition: University of Corunna Dissertation Award, 2003 Best Paper Award at LPNMR 2019 Best Student Paper at ICLP 2020 Best Student Paper at JELIA 2019 Grants & projects: He currently leads or co-leads nationally funded Spanish projects (GEISER 2024-2028, ARLEKIN 2021-2024) and has coordinated EU COST actions (DigForASP) as well as earlier MINECO projects on temporal ASP and medical reasoning (TARDIS, MERLOT, FEAST, etc.). PhD supervision: He has successfully supervised three PhD theses (Martín Diéguez, Jorge Fandiño, Brais Muñiz) and continues to advise students within the Information Retrieval Laboratory (IRLab) and the Spanish node of Potassco Solutions.

Federico DivinaView profile

Professor

• Bioinformatics
• Evolutionary Computation
• Machine Learning
• +5 more

Federico Divina is a Professor in the Department of Sports and Computer Science at Universidad Pablo de Olavide, Spain. His research focuses on evolutionary computation, machine learning, and bioinformatics. PhD in Artificial Intelligence from Vrije Universiteit Amsterdam Former postdoc at University of Tilburg (NEWTIES EU project) Research Interests : Bioinformatics, Evolutionary Computation, Machine Learning, Big Data, and Soft Computing. He specializes in knowledge extraction from massive datasets through genetic algorithms and heuristic optimization. Recent Publications span time series forecasting, feature selection in high-dimensional data, and biomedical image analysis. His work combines evolutionary algorithms with practical applications in energy consumption prediction, ocular disease diagnosis, and genomic data analysis. Labs & Collaborations : Leads the DS&BD Data Science & Big Data Lab and has collaborated with groups like DATAi and DASE. His projects include Differential (multi-university energy analysis), GALICIAME (SMA genetic data analysis), and NEWTIES (artificial society modeling).

Simo AlamiView profile

Tutor

• Deep Learning
• Reinforcement Learning
• Inverse Reinforcement Learning
• +4 more

Simo Alami is a Ph.D. candidate and Tutor at Ecole Polytechnique, affiliated with the LIX computer science laboratory under the supervision of Professor Jesse Read. He teaches tutorials for the Advanced Machine Learning and Autonomous Agents course (Computer Science, Ingénieur 3A/Master1) since 2020, focusing on practical implementations of machine learning algorithms and autonomous systems. His academic background includes undergraduate and graduate studies in Mathematics and Computer Science at Université Pierre et Marie Curie and Ecole CentraleSupélec. Ph.D. Candidate, Ecole Polytechnique (2020-Present) Master's Studies, Mathematics and Computer Science, Université Pierre et Marie Curie and Ecole CentraleSupélec Alami's research centers on developing algorithms that learn from experience through self-learned metrics, with core expertise in Deep Learning, Inverse Reinforcement Learning, and Metric Learning. His work targets robotic applications where agents must perform novel tasks by understanding logical concepts, while also extending to energy management systems through non-invasive load monitoring. He explores how meta-learning frameworks can enable transferable reward structures across domains. His publication record reveals a strong trajectory in distributional reinforcement learning and inverse reinforcement learning using generative models, with significant contributions to metric learning for clustering and energy disaggregation. The consistent focus on transferable methodologies across robotics and smart grid applications demonstrates his interdisciplinary approach to solving real-world problems through advanced machine learning techniques. Scientific recognition includes: Nvidia Grant awarded in 2022 for research on Meta-Inverse Reinforcement Learning 3rd Prize at Hi Paris Hackathon (2021) for a reinforcement learning-based smart grid energy management solution While not supervising graduate students as a Ph.D. candidate, Alami has secured competitive external funding including the Nvidia research grant. His industry collaboration with Accenta during a visiting researcher position resulted in ECML 2022 publications on non-invasive load monitoring, highlighting his ability to bridge academic research with practical engineering applications. As an active member of the LIX laboratory at Ecole Polytechnique, Alami participates in cutting-edge computer science research while maintaining external collaborations. His visiting researcher position at Accenta demonstrates engagement with industry partners, and his organization of the IRT SystemX Electromobilité et territoires webinar in 2021 reflects leadership in knowledge dissemination within the energy and mobility research community.

Luis Antonio Belanche MuñozView profile

Professor

• Machine Learning
• Kernel Methods
• Neural Networks

Luis Antonio Belanche Muñoz is a Professor at the Department of Computer Science , Faculty of Informatics of Barcelona (FIB) , Universitat Politècnica de Catalunya (UPC) . He is affiliated with research groups SOCO - Soft Computing and IDEAI-UPC - Intelligent Data Science and Artificial Intelligence Research Group . His career spans over 25 years, with 216 documented activities. His research focuses on Machine Learning , Kernel Methods , and Neural Networks . He has pioneered techniques in feature selection, similarity measures, and hybrid models connecting deep learning with kernel methods. His work applies to diverse domains including finance, microbiology, cancer diagnostics, and environmental engineering. Recent publications highlight trends in kernel matrix analysis using entropy, microbiome data integration , and drug resistance prediction in HIV. Earlier work includes knowledge-based systems for wastewater treatment diagnostics and educational technologies for MOOC environments. He has collaborated with 75+ researchers across UPC's research network, contributing to projects funded under Spain's State Research Plans and Catalonia's RIS3CAT strategy. His 2011 thesis on Feature selection in brain tumor MRS data demonstrates interdisciplinary applications.

Martha Ivon Cárdenas DomínguezView profile

Senior Lecturer

• Intelligent Data Analysis
• Machine Learning
• Personalized Medicine
• +3 more

Dr. Martha Ivon Cárdenas Domínguez is a Senior Lecturer at the Universitat Politècnica de Catalunya (UPC), affiliated with the Department of Computer Science. She is an active member of the IDEAI-UPC - Intelligent Data sciEnce and Artificial Intelligence Research Group, as well as the SOCO (Soft Computing) research group. Education: BSc in Mathematics PhD in Artificial Intelligence (UPC) Master's in Artificial Intelligence Her research focuses on applying computational intelligence and machine learning techniques to biomedical data analysis, particularly for pharmacoproteomic applications involving G protein-coupled receptors. She specializes in kernel-based methods and data visualization techniques for sequence analysis and classification tasks. Recent publications demonstrate her expertise in manifold learning, subtype discrimination of GPCRs, and phylogenetic tree integration with visualization techniques. Her work addresses challenges in classification errors, mislabeling, and sequence transformation for complex biomedical datasets. Dr. Cárdenas employs advanced visualization strategies to explore metabotropic glutamate receptors and analyze protein sequence overlaps through manifold-based approaches. Her research bridges computational methods with biomedical applications, particularly in personalized medicine contexts. She actively contributes to competitive R&D+i projects and participates in international conferences. Her professional activities include 5 conference presentations, 2 book chapters, and 2 journal articles focusing on data science applications in bioinformatics. Dr. Cárdenas utilizes computational intelligence for analyzing receptor sequences and has developed innovative approaches for visualizing complex biological data structures. Her work has implications for drug discovery and personalized treatment development through enhanced understanding of receptor classification.

Mark SteelView profile

Professor

• Bayesian Statistics
• Econometrics
• Distribution Theory
• +7 more

Professor Mark Steel is a faculty member at the University of Warwick , serving as Professor of Statistics since 2003. He previously held a Chair in Economics at the University of Edinburgh (1998-2000) and a Chair of Statistics at the University of Kent (2000-2003). He has also served as Head of the Statistics Department at Warwick (2014-2018) and as Editor-in-Chief of Bayesian Analysis (2022-2025). Education: Ph.D. in Quantitative Economics from Université Catholique de Louvain (1987) Steel's research focuses on Bayesian econometrics and statistics , with interests in distribution theory, model averaging, spatial statistics, nonparametric inference, survival analysis, and stochastic volatility. His work bridges theoretical advancements with applications in macroeconomics (growth theory) , microeconomics (stochastic frontier models) , and finance (stochastic volatility) . Recent publications highlight his contributions to Bayesian computation , copula-based classification , and spatiotemporal modeling . His editorial roles include leadership in Bayesian Analysis and Journal of Productivity Analysis . Scientific Awards: Fellow of the Journal of Econometrics Steel co-leads the Centre for Research in Statistical Methodology (CRiSM) at Warwick and has secured grants such as the EPSRC GR/T17908/01 for flexible distributional modeling in panel data. His collaborations span institutions in the UK, Spain, Italy, and the Netherlands, with co-authors like Roberto Casarin and Jairo Fúquene.

• Machine Learning
• Computer Vision
• Robotics
• +5 more

Roberto Javier López Sastre is an Associate Professor of Signal Theory and Communications at the University of Alcalá. He holds a Ph.D. from the same institution (2010), focusing on 'Visual vocabularies for category-level object recognition' under Dr. Saturnino Maldonado Bascón's supervision. His research spans machine learning, computer vision, robotics, and astrophysics. Key areas include Bayesian neural networks for stellar dating, semantic navigation in robotics, and AI-driven medical assistive technologies. Affiliation: Department of Signal Theory and Communications, University of Alcalá Research Group: GRAM (Multisensorial Recognition and Analysis Group) His work interfaces computational methods with real-world applications, such as assistive robotics for neurodevelopmental disorder patients and deep learning models for astrophysical parameter estimation. Recent contributions include semantic segmentation-driven navigation systems and Bayesian approaches to black hole solutions. Publications emphasize interdisciplinary applications of AI, including live video processing, continual learning frameworks, and physics-informed neural networks. Ongoing research explores the intersection of robotics, healthcare, and astrophysics through collaborative projects. López Sastre's GRAM group focuses on multisensory data analysis for recognition and navigation challenges. His technical expertise spans signal processing, probabilistic modeling, and embedded AI systems.

David Garrido RomeroView profile

Professor

• Maritime History
• Archival Science
• Historiography
• +3 more

David Garrido Romero is a Professor of Historiographic Sciences and Techniques at the University of Cádiz , actively engaged in maritime history and archival research. As a PhD candidate at CEIMAR (Campus of International Excellence for the Sea) and holder of two master's degrees – one in Maritime Heritage, Archaeology, and History (University of Cádiz, Extraordinary Master's Award ) and another in Documents, Books, Archives, and Libraries (University of Seville) – his academic foundation is robust. His work bridges maritime history, notarial documentation, and digital humanities. Research interests span 18th-19th century maritime history from notarial/documentary perspectives, with specific focus on: Maritime notarial institutions Underwater cultural heritage Historical manuscript digitization Global communication nodes in colonial contexts Archival metadata systems His recent publications highlight maritime legal frameworks, AI applications in archival work, and transatlantic cultural connections. He has participated in critical conferences at international venues (2016-2024) and received recognition for his work on Cádiz' maritime heritage. The Caravel Project (2018-2019) demonstrates his innovative approach to combining maritime archaeology with artificial intelligence. Key scientific contributions include: Developing probabilistic indexing methods for historical documents Digitizing 3200+ notarial maritime records Establishing archival metadata standards for maritime heritage Analyzing Bourbon dynasty reforms through notarial sources His work creates bridges between archival science, maritime archaeology, and digital humanities, ensuring historical sources remain accessible for modern research.

Anna De Mier VinueView profile

Associate Professor

• Combinatorics
• Graph Theory
• Matroid Theory
• +3 more

Anna De Mier Vinue is an Associate Professor at the Department of Mathematics, Universitat Politècnica de Catalunya (UPC), affiliated with the Facultat d'Informàtica de Barcelona (FIB). She leads research in combinatorics, graph theory, and matroid theory as part of the UPC's GAPCOMB research group (Geometric, Algebraic and Probabilistic Combinatorics). Her work focuses on structural combinatorics, polynomial invariants, and discrete geometry. Education: Holds a PhD in Applied Mathematics from UPC. Research Interests: Combinatorial enumeration, graph polynomials (Tutte, U-polynomials), matroid representations, non-crossing structures, and algorithmic combinatorics. Her contributions bridge algebraic methods with geometric and probabilistic approaches. Publications: Over 77 works including articles in Discrete Mathematics, European Journal of Combinatorics, and SIAM Journal on Discrete Mathematics. Recent research explores marked graphs, Tutte polynomial evaluations, and lattice approximations in clutter theory. Active in international projects like COCOA and R+D+I initiatives. Grants & Collaborations: Co-leads projects on extremal combinatorics, geometric algorithms, and mathematical education. Collaborates with researchers from BarcelonaTech and international institutions. Involved in initiatives addressing gender equality in STEM education through statistical analysis. Labs/Teams: Core member of the UPC's GAPCOMB group, contributing to interdisciplinary projects at the Institut de Matemàtiques de la UPC-BarcelonaTech. Supervises research in combinatorial geometry and algebraic structures.

Víctor López DomínguezView profile

Assistant Professor

• Spintronics
• Magnetic materials
• Electrical transport
• +5 more

Víctor López Domínguez is an Assistant Professor and Principal Investigator at the Institute of Advanced Materials (INAM) of Jaume I University in Castelló, Spain, where he leads the Spintronics for Advanced Devices Lab (SPINAD Lab). His research focuses on developing next-generation spintronic devices for computing and sensing applications. His academic background includes: PhD in Nanoscience and Nanotechnology (2014) from University of Barcelona Physics Degree (2009) from University of Barcelona López Domínguez's research centers on electrical transport in magnetic materials, magnetization dynamics, and voltage-controlled spintronic devices. His work bridges fundamental physics with practical applications in neuromorphic computing, probabilistic systems, and nanoscale sensors. Key focus areas include antiferromagnetic spintronics, skyrmion manipulation, and energy-efficient computing paradigms that leverage spin-orbit torque and voltage control mechanisms. His 15 most recent publications reveal a strong emphasis on antiferromagnetic memory devices, voltage-controlled magnetism, and neuromorphic applications. The research spans from fundamental material studies to device integration, with significant contributions to silicon-compatible spintronic memory, probabilistic computing hardware, and magnetomechanical sensors. His scientific recognition includes: CIDEGENT grant (2022) from Generalitat of Valencia López Domínguez secured the CIDEGENT grant to establish his research group at INAM, supported by Jaume I University and INAM. His lab trains undergraduate, master's, and PhD students in experimental spintronics while collaborating with international clean rooms and industry partners. Current projects focus on implementing novel computing paradigms using spintronic devices. The SPINAD Lab maintains comprehensive facilities for material fabrication, device characterization, and nanofabrication through Spanish clean room networks. The group collaborates extensively with Northwestern University (where López Domínguez previously worked) and participates in international research consortia focused on next-generation computing technologies.

FRANCISCO JAVIER GARCIA POLOView profile

Professor

• Artificial Intelligence
• Reinforcement Learning
• Robotics
• +4 more

Francisco Javier Garcia Polo is a Professor at the University of Santiago de Compostela (USC) , affiliated with the Department of Electronics and Computing within the Higher Polytechnic School of Engineering . His research focuses on Reinforcement Learning (RL) , particularly in areas such as safe decision-making, adversarial attack detection, and policy transfer across tasks. He holds a PhD from Universidad Carlos III de Madrid (2013), where his thesis explored safe RL in continuous state-action spaces. Key research interests include enhancing RL robustness against adversarial attacks, federated learning applications in robotics, and applying RL to financial systems like automated market makers. He is part of the GSI Group (Intelligent Systems Group) , contributing to projects involving social assistive robotics and multi-modal transportation planning tools like TIMIPLAN. His work bridges theoretical advancements with practical domains such as healthcare robotics, cybersecurity, and economic modeling. Publications highlight innovations in policy defense mechanisms, similarity metrics between Markov Decision Processes, and frameworks for evaluating assistive robots. Despite his prolific output, he has not publicly shared research papers on Academia.edu. Collaborations span interdisciplinary topics, reflecting a commitment to both foundational AI research and real-world applications.

• High-energy particle phenomenology
• Quantum computing for scattering amplitudes
• Loop-tree duality
• +3 more

Germán Rodrigo is a tenured Research Professor at the Instituto de Física Corpuscular (IFIC) , a joint centre of the Spanish National Research Council (CSIC) and the University of Valencia . After earning his PhD in 2003 under Arcadi Santamaria, he held post-doctoral positions at KIT Karlsruhe and CERN before returning to Valencia in 2008. He currently leads the quantum–phenomenology group within the theoretical physics department. His research straddles high-energy collider phenomenology and quantum computing. Rodrigo is internationally recognised for turning multi-loop Feynman integrals into causal, loop-tree-dual forms and for implementing the resulting algorithms on real quantum hardware. Key achievements include the first quantum calculation of loop integrals, quantum jet clustering at the LHC, and quantum amplitude estimation with error mitigation. Recent work (2022-2025) focuses on: Quantum integration of decay rates and fragmentation functions Graph-based quantum algorithms for causal multi-loop configurations Adaptive importance sampling on quantum annealers and gate-based devices Factorisation-breaking studies in triple-collinear splitting with massive partons He advises three doctoral students and is PI on a national Spanish grant supporting the group’s quantum-technologies programme. No personal e-mail is publicly listed; contact is handled through the IFIC secretariat.

Ankush DasView profile

Assistant Professor

• Programming Languages
• Cryptographic Protocols
• Distributed Systems
• +6 more

Ankush Das is a tenure-track assistant professor in the Computer Science Department at Boston University. His research focuses on programming languages with applications in cryptographic protocols, distributed systems, and probabilistic and machine learning models. Prior to joining Boston University, he worked as an applied scientist at Amazon in the Automated Reasoning Group until December 2023. Dr. Das received his PhD from Carnegie Mellon University in 2021, where he was advised by Prof. Jan Hoffmann and worked closely with Prof. Frank Pfenning. He completed his undergraduate studies at IIT Bombay, India in 2015. His research interests span a wide range of topics within programming languages, with specific focus on resource analysis, session types, distributed protocols, and language design for smart contracts on the blockchain. He is particularly interested in developing type systems that can ensure safety and efficiency properties in concurrent and distributed systems. His work has led to the development of domain-specific languages like Nomos for implementing smart contracts and Rast for resource-aware session types with arithmetic refinements. Dr. Das's publication record demonstrates a consistent focus on advancing type theory and its applications to practical systems. His work frequently appears in top-tier programming languages conferences such as POPL, PLDI, and ICFP. A notable trend in his recent work is the extension of session types to handle probabilistic computations and resource-aware programming, reflecting the growing importance of these areas in modern distributed systems. His scientific achievements have been recognized with several prestigious awards: Distinguished paper award at POPL 2024 for "Parametric Subtyping for Structural Parametric Polymorphism" Best system description paper award by a junior researcher at FSCD 2020 for "Rast: Resource-Aware Session Types with Arithmetic Refinements" Dr. Das is actively mentoring PhD and undergraduate students at Boston University. His current advisees include Anthony DeRossi, Toby Ueno, Brendan Coyne, Qiancheng Fu, June Wunder, Sam Buxbaum, and Sakshi Sharma. He is looking for motivated PhD students to join his research group, with opportunities to work on cutting-edge problems in programming languages and their applications to distributed systems and security. At Boston University, Dr. Das leads research efforts in programming language theory and its applications. His work bridges theoretical foundations with practical implementations, particularly in the areas of smart contracts and distributed protocols. He has collaborated extensively with researchers from Carnegie Mellon University, including his former advisors Jan Hoffmann and Frank Pfenning.

• Biomedical Signal Processing
• Respiratory Analysis
• Cardiovascular Monitoring
• +2 more

Daniel Romero Pérez is a Lecturer at the Department of Systems Engineering, Automation and Industrial Informatics within the Barcelona East School of Engineering (EEBE) at Universitat Politècnica de Catalunya (UPC). He maintains a research affiliation with the Institute for Bioengineering of Catalonia (IBEC) and leads projects in the BIOSPIN group focused on Biomedical Signal Processing and Interpretation. His research centers on biomedical signal processing with applications in respiratory/cardiac monitoring and disease diagnostics. Key interests include: Developing machine learning models for obstructive sleep apnea detection using ECG and respiratory signals Analyzing heart rate variability in cardiovascular disorders like Brugada syndrome Creating non-invasive respiratory monitoring systems for COPD patients Investigating hypoxia effects on cardiac electrophysiology Publication analysis (29 conference papers, 18 journal articles) reveals consistent focus on: Algorithm development for physiological signal interpretation Clinical validation of wearable sensors Multivariate modeling of cardiorespiratory pathologies Translational research bridging engineering and clinical medicine He collaborates extensively with European institutions on competitive R&D projects including 'Smart Health Ecosystem for Breathing Illnesses' and 'Unintrusive Remote Health Assessment'. Research outputs demonstrate strong emphasis on practical healthcare solutions with 16 open-access publications.