جستجوی استاد راهنمای دانشگاهی

• Machine Learning
• Deep Learning
• Anomaly Detection
• +۵ مورد دیگر

Peter Karsmakers serves as Associate Professor at KU Leuven's Department of Computer Science within the Faculty of Engineering Technology, based at the Geel Campus. He coordinates the Declarative Languages and Artificial Intelligence (DTAI) research group and holds leadership roles including coordinator of Research and Education for Computer Science across Geel and Diepenbeek Campuses. Karsmakers earned his PhD in Engineering Science in May 2010, focusing on kernel-based learning algorithms for sparse modeling and efficient predictions from large datasets. His doctoral work established foundations for his current research trajectory in resource-constrained machine learning systems. His research integrates machine learning with signal processing for real-time sensor data interpretation, specializing in anomaly detection from acoustic, radar, and accelerometer signals on embedded devices. Current projects address industrial condition monitoring, elderly care systems, and livestock facility monitoring through three main tracks: acoustic monitoring (e.g., SINS, WATCHDOG), radar-based systems (e.g., FARADAY, NextPerception), and smart electronics for power converters. Recent publications demonstrate strong trends in constraint-guided deep learning architectures for industrial applications, cross-environment robustness in sensor systems, and domain-knowledge integration to reduce data requirements. His work consistently bridges theoretical machine learning with practical implementations in resource-constrained environments. No scientific awards or fellowships were mentioned in the provided materials. Karsmakers supervises over 10 master's theses annually and coordinates a research team of 10 PhD students and a post-doc within DTAI-ADVISE. He has secured approximately 2.3 million euros in funding through VLAIO, EU-ECSEL, and bilateral industry contracts, including 10 active projects such as AutoEdgeML (2024-2028) and Fault Tolerant Neural Networks for Space Applications (2024-2027). He leads the DTAI-ADVISE research group focused on developing software that attaches semantics to sensor data on resource-constrained devices. The team operates across multiple campuses with specialized labs for acoustic monitoring (Geel), radar-based systems (in collaboration with ESAT-TELEMIC), and smart electronics (with Electrical Engineering department), maintaining strong industry partnerships with companies in healthcare, manufacturing, and agriculture sectors.

• Materials Science
• Manufacturing Engineering
• Additive Manufacturing
• +۳ مورد دیگر

Robrecht Abts is a researcher at KU Leuven’s Manufacturing Processes and Systems (MaPS) group, affiliated with the De Nayer Campus. His work bridges electromechanics, materials science, and advanced manufacturing techniques. His research focuses on structure, behavior, and sustainability of materials , with particular emphasis on thermal analysis in additive manufacturing processes like fused filament fabrication (FFF). This includes leveraging deep learning for real-time thermal data interpretation and optimizing electrical discharge machining (EDM) through adaptive pulse classification. Recent publications highlight his expertise in Threshold-free machine learning pipelines Thermal modeling in 3D printing COMSOL simulations for manufacturing processes

• Signal processing
• Fault detection and diagnosis
• Rotordynamics
• +۷ مورد دیگر

Konstantinos Gryllias is a Professor in the Department of Mechanical Engineering at KU Leuven's Faculty of Engineering Sciences. He leads research in the Mechatronic System Dynamics (LMSD) unit at the Arenberg campus. His academic affiliations extend across multiple KU Leuven institutes including Leuven.AI, Leuven.AM (Additive Manufacturing), and the Gravitation Institute. He serves on important governance bodies as a member of the Faculty Council of Engineering Sciences, Faculty Doctoral Committee of Engineering Sciences, and Departmental Council of Mechanical Engineering. Dr. Gryllias specializes in signal processing, fault detection and diagnosis of rotating machinery, condition monitoring, and machine learning applications in structural health monitoring. His research spans linear and nonlinear vibrations, anomaly detection, rotordynamics, and pattern recognition. His work bridges theoretical signal processing with practical engineering applications in wind turbines, marine propulsion systems, and industrial machinery. His recent publications demonstrate strong focus on deep learning approaches for wind turbine anomaly detection, bearing diagnostics, stern bearing lubrication optimization, and structural health monitoring using advanced signal processing techniques. The research shows increasing integration of explainable AI methods with traditional vibration analysis. Dr. Gryllias teaches advanced courses including Monitoring & Prognostics, Structural Dynamics, Smart Sensing Technologies, and Applied AI perspectives. His teaching portfolio reflects the interdisciplinary nature of his research, connecting mechanical engineering fundamentals with cutting-edge AI methodologies. He currently leads multiple research projects through 2025-2029, primarily as Promotor, focusing on fault detection in gears using fiber optic sensors, multi-sensor monitoring of drivelines, physics-inspired machine learning for condition monitoring, and digital twin applications for wind turbine efficiency improvement.

Jef Vandemeulebrouckeمشاهده پروفایل

پژوهشگر

• Medical Imaging
• Computer Vision
• Artificial Intelligence
• +۳ مورد دیگر

Jef Vandemeulebroucke is a researcher at the Department of Electronics and Informatics , Vrije Universiteit Brussel (VUB) , specializing in medical imaging, computer vision, and augmented reality applications in healthcare. His work bridges artificial intelligence with radiology and biomechanics , focusing on automated segmentation, predictive modeling, and real-time surgical navigation systems. Research interests include: Medical image analysis for disease prognosis (e.g., COVID-19 severity , neurosurgical drains ) Development of MedShapeNet , a 3D medical shape dataset for computer vision Augmented reality systems in orthopedic and neurosurgical interventions AI-driven fluorescence endoscopy and dynamic CT for joint kinematics Key trends in his 140+ publications emphasize deep learning , image registration , and 4D-CT applications . Supervised theses include brain age prediction and chest radiography automation. Active in 38 projects (e.g., AI-NIMO , TumorScope ), he collaborates with institutions like the Universitair Ziekenhuis Brussel (UZB) and FWO (Fund for Scientific Research-Flanders).

Orphée De Clercqمشاهده پروفایل

استادیار

• Natural Language Processing
• Machine Learning
• Readability Prediction
• +۷ مورد دیگر

Orphée De Clercq is an Assistant Professor at Ghent University, specializing in language technology for educational applications. Her research focuses on leveraging Natural Language Processing (NLP) and Machine Learning (ML) to enhance computer-assisted language learning , readability prediction , and automated writing evaluation . She also explores sentiment analysis , emotion detection , and event coreference resolution in Dutch and multilingual contexts. Education : PhD in 2015 with groundbreaking work in readability prediction and fine-grained sentiment analysis for Dutch. Research Trends in her recent publications emphasize: Readability across domains and languages Emotion Detection using transformers and affect lexica Event Coreference in cross-document news Automated Writing Evaluation through NLP Implicit Sentiment Analysis in user-generated content Cross-Lingual Transfer with multilingual datasets She co-supervises four PhD students and contributes to interdisciplinary projects like Steunpunt Toetsen , SentEMO , and NewsDNA . Her teaching includes courses on digital communication and Computer-Assisted Language Learning .

Pieter Simoensمشاهده پروفایل

استادیار

• Distributed Artificial Intelligence
• Edge Computing
• Algorithms for Neuromorphic Computing
• +۲ مورد دیگر

Pieter Simoens is an Assistant Professor at Ghent University and affiliated with the imec research institute. He works at the intersection of distributed artificial intelligence, edge computing, and collective intelligence, with a focus on AI applications for resource-constrained environments and robotic systems. His research explores innovative approaches to machine learning deployment in heterogeneous infrastructures, task planning for IoT-integrated robotics, and modeling collective decision-making processes. He has contributed to frameworks like DIANNE for distributed deep learning and developed methods for cognitive modeling in reinforcement learning scenarios. With over 100 publications, his recent work spans adaptive neural networks, privacy-preserving surveillance, UAV hyperspectral data analysis, and computational fairness in AI systems. He leads research initiatives within the Internet Technology and Data Science Lab (IDLab) and contributes to educational programs in software engineering and applied machine learning. Responsible for courses on software engineering, mobile development, system design, and applied machine learning Active in edge computing and neuromorphic algorithms research Develops AI solutions for robotics, surveillance, and industrial IoT applications

Damien Ernstمشاهده پروفایل

استاد

• Energy Systems
• Operations Research
• Remote Renewable Energy Hubs
• +۵ مورد دیگر

Prof. Damien Ernst is a faculty member at the Montefiore Institute, Department of Electrical Engineering and Computer Science, University of Liège (Belgium). His research focuses on energy systems, remote renewable energy hubs, reinforcement learning, and optimization algorithms. He actively contributes to decarbonization strategies for hard-to-abate sectors like shipping and aviation. Academic Rank: Professor University: University of Liège School: Montefiore Institute Department: Electrical Engineering and Computer Science Research interests include: Design and techno-economic analysis of remote renewable energy systems Reinforcement learning applications in energy and optimization Energy transition policy and sustainability modeling Machine learning techniques for energy system transparency Integration of nuclear, hydrogen, and battery technologies His recent publications demonstrate expertise in: Remote Renewable Energy Hub (RREH) design Small Modular Reactor (SMR) integration Asymmetric Actor-Critic algorithms Energy system optimization and modeling Grid stability and hosting capacity analysis Explainable AI for closed-domain question answering Prof. Ernst leads PhD projects at the intersection of Operations Research and Energy Systems, focusing on energy systems models' transparency and optimization techniques.

• Industrial Artificial Intelligence
• Digital Twin Technology
• Condition Monitoring
• +۷ مورد دیگر

Pradeep Kundu serves as an Assistant Professor in the Department of Mechanical Engineering at KU Leuven's Faculty of Engineering Technology (Bruges Campus), where he leads the M-Group Asset Performance Management subdivision. He is an active member of Leuven.AI Institute for Artificial Intelligence and holds governance roles in the Mechanical Engineering Department Council and Faculty Council. His research centers on Industrial Artificial Intelligence integrated with Digital Twin Technology, focusing on three core domains: rotating machinery condition monitoring (fault diagnosis/prognosis), manufacturing quality control (tool wear/surface monitoring), and production process optimization. Key methodological contributions address data scarcity through synthetic data generation (Digital Twin/Generative AI) and enhance model robustness via Physics-Informed Machine Learning, Hybrid Modeling, and advanced Statistical Regression. Analysis of his 15 most recent publications (2024-2025) reveals a dominant focus on predictive maintenance for mechanical systems, utilizing diffusion models for damage imaging, entropy-based domain adaptation for bearing failure prediction, and sensor fusion techniques. His work consistently bridges physics-based modeling with deep learning across rotating machinery, structural health monitoring, and smart manufacturing applications. Dr. Kundu currently leads multiple funded projects including 'Intelligent Prognosis of Rotating Machines in Industry 4.0 using Generative AI' (2024-2025) and 'Digital Twin Framework for Fleet-Level Feed Drive Systems Health Assessment' (2023-2027), addressing critical challenges in data-limited industrial AI deployment. His research directly supports Industry 4.0 transformation through maintenance optimization and quality control innovations. He actively contributes to academic governance as member of the OC Smart Operations and Maintenance in Industry committee and the Mechanical Engineering Department Council, while his research group within the Mecha(tro)nic System Dynamics unit develops practical AI solutions for industrial asset performance management.

Chris Develderمشاهده پروفایل

دانشیار

• Natural language processing
• Information extraction
• Smart grid
• +۲ مورد دیگر

Chris Develder is an Associate Professor with the research group IDLab in the Department of Information Technology (INTEC) at Ghent University - imec, Ghent, Belgium. He received his MSc degree in computer science engineering and PhD in electrical engineering from Ghent University in Jul. 1999 and Dec. 2003 respectively (as a fellow of FWO). He has held research visitor positions at UC Davis, CA, USA (Jul.-Oct. 2007) and at Columbia University, NY, USA (Jan. 2013 - Jun. 2015). Prof. Develder leads two research teams within the Internet Technology and Data Science Lab (IDLab): one focused on converting text to knowledge (NLP, primarily information extraction using machine learning), and another on data analytics and machine learning for smart grids. His Text-to-Knowledge (T2K) research group has a strong track record in information extraction across various domains including news, human resources, and biomedical applications, as well as text classification tasks such as sentiment analysis. More recently, the group has expanded into conversational agents and generative models for educational applications. With his team, Prof. Develder has published over 200 papers in international journals and conferences including EMNLP, CoNLL, EACL, ACL, ECIR, CIKM, WSDM, WWW, and NIPS. His recent publications demonstrate a growing focus on practical applications of NLP in healthcare (personality style recognition from speech, biomedical adverse drug event extraction), education (question generation, gap-filling exercises), and labor market analysis (career path prediction, skill extraction). His work bridges theoretical advances in machine learning with real-world applications across multiple domains. Prof. Develder actively supervises PhD students and has co-supervised numerous successful doctorates, including Maarten De Raedt (2024), Semere Kiros Bitew (2024), Yiwei Jiang (2024), Amir Hadifar (2023), and Klim Zaporojets (2022). His former students have gone on to work at organizations including EarlyTracks, Zoom, Nokia Bell Labs, Clarivate, and various academic institutions.

Lennart Martensمشاهده پروفایل

استاد

• Bioinformatics
• Biomedical Analytics
• Predictive Modelling
• +۵ مورد دیگر

Lennart Martens is a Professor of Systems Biology at Ghent University and serves as Group Leader and Associate Director at the VIB-UGent Center for Medical Biotechnology . He leads the Computational Omics and Systems Biology Group (CompOmics), focusing on Machine Learning applications in high-throughput omics data. His research involves developing AI-driven algorithms for proteomics data analysis, including tools like DeepLC for retention time prediction and MS2Rescore for improved peptide identification. He contributes to open-source proteomics software and FAIR data practices. Fellow of the Royal Society of Chemistry Prometheus Award for Research Excellence (Ghent University, 2014) Juan Pablo Albar 'Proteomics Pioneer' Award (European Proteomics Association, 2015) He has authored over 220 research papers, co-authored two Wiley textbooks on mass spectrometry bioinformatics, and organized Dagstuhl Seminars on computational proteomics. His editorial roles include membership on the boards of Molecular & Cellular Proteomics , Molecular BioSystems , and PeerJ .

• Reinforcement Learning
• Artificial Intelligence
• Robotics
• +۳ مورد دیگر

Ann Nowe is a Professor at the Department of Electronics and Informatics (ETRO) at Vrije Universiteit Brussel. Her research focuses on reinforcement learning, multi-agent systems, robotics, and energy management. She leads the Federated labs AI and Robotics, emphasizing interdisciplinary collaboration in artificial intelligence and sustainable robotics. With a prolific publication record (555+ outputs) and 152 active projects, her work spans theoretical advancements and applied solutions in AI ethics, explainability, and energy systems. Her research interests include AI security, neuro-symbolic integration, and federated robotics. Notable contributions include frameworks for explainable AI in multi-agent environments and predictive maintenance algorithms for wind turbines. She has received multiple awards, including the ALA Best Paper Award (2018) and Best Demonstration Award (2019). Dr. Nowe actively participates in conferences and workshops on trustworthy AI, co-organizing events like the World Conference on eXplainable AI (2025). Her work integrates ethical considerations and human-centric design principles across robotics, energy systems, and collective decision-making.

Federico Holikمشاهده پروفایل

پژوهشگر ارشد

• Foundations of Quantum Mechanics
• Quantum Information Theory
• Quantum Logic
• +۳ مورد دیگر

Federico Holik serves as a Research Fellow at Argentina's National Scientific and Technical Research Council (CONICET) with primary affiliation to Vrije Universiteit Brussel (VUB) in Belgium. His institutional presence is anchored through VUB's CRIS profile and publications portal, reflecting active engagement in quantum research despite the absence of specified departmental or school affiliations within the university structure. His research program critically examines the logical, algebraic, and geometrical frameworks underpinning quantum mechanics, with concentrated efforts in quantum information theory and foundational probability interpretations. Key investigations include quantum resource management for NISQ-era devices, ontological indistinguishability of quantum entities, and the development of quantum mereology to address part-whole relationships in quantum systems. His interdisciplinary reach extends to quantum-inspired AI through quasi-set theory and epidemiological applications via information quantifiers in pandemic data analysis. Analysis of his 2023-2025 publications reveals two dominant trajectories: (1) practical quantum computing challenges centered on resource optimization, error mitigation, and software engineering frameworks for noisy hardware, and (2) deep foundational inquiries into quantum ontology, probability structures, and mereological paradoxes. This dual focus bridges theoretical rigor with emerging quantum technologies while maintaining strong connections to philosophical questions about quantum identity and agency.

Dirk Van den Poelمشاهده پروفایل

استاد

• Data Analytics
• Streaming Processing Frameworks & Analytics
• Internet of Things (IoT) & Industry 4.0
• +۲ مورد دیگر

Dirk Van den Poel is a Professor of Data Analytics/Big Data at Ghent University, Belgium, specializing in statistical computing, social media analytics, and predictive modeling. He has co-founded pioneering academic programs including the first predictive analytics master’s program globally, the Master of Science in Statistical Data Analysis, and the Master of Science in Business Engineering/Data Analytics. Teaches courses: Statistical Computing, Big Data, Social Media Analytics Research focus: Analytical CRM, ensemble classification methods, big data 110+ ISI-indexed publications in journals like IEEE Transactions on Power Systems and Decision Support Systems His recent work explores topics such as rumor detection in social media, predictive maintenance using sensor data, and crisis response through service adaptation. He leverages machine learning and deep learning for applications in agriculture, healthcare, and energy sectors. Current projects involve topic modeling (BERTopic), credit scoring with interpretable models, and spatiotemporal crime prediction using mobile phone data. Dirk’s methodology integrates stream processing frameworks , reinforcement learning , and ensemble techniques .

Valentin Delchevalerieمشاهده پروفایل

پژوهشگر

• Machine Learning
• Anomaly Detection
• Image Processing
• +۶ مورد دیگر

Valentin Delchevalerie is a researcher at the Faculty of Computer Science, University of Namur , affiliated with the Research Center on Information Systems Engineering and the Namur Institute for Complex Systems. Their work focuses on integrating mathematical and physical principles into deep learning architectures. Key projects: Bessel-CNNs (rotation-invariant image recognition), Quaternion Convolutions for 3D imaging, and Cycle-Consistent GANs for anomaly detection. Research spans machine learning , image processing , and computational physics , with applications in both industrial process monitoring and medical diagnostics . Their publications emphasize rotation equivariance , fairness constraints , and visualization techniques . Notable collaborations include work with Benoît Frénay (UNamur), Adrien Mayer (UNamur), and teams in medical imaging and materials science . The 15 most recent articles highlight advancements in 3D image analysis , medical anomaly detection , and physics-informed neural networks .

• Deep Learning
• Image Processing
• Computer Vision
• +۳ مورد دیگر

Evangelia Tsiligianni is a postdoctoral researcher in the Department of Electronics and Informatics at Vrije Universiteit Brussel , Belgium. Her work focuses on deep learning, image processing, and computer vision, particularly for multimodal image restoration and super-resolution tasks. Active in deep learning and neural networks . Specializes in image resolution , compressed sensing , and medical imaging . Her recent research explores graph regularization for depth map super-resolution and interpretable deep learning in financial and healthcare domains. She has presented at conferences like ICASSP, MICCAI, and EUSIPCO.