Rasmus Froberg Brøndum is an Associate Professor of Bioinformatics and Biostatistics at Aalborg University Hospital, affiliated with the Department of Clinical Medicine and the Center for Clinical Data Science under the Faculty of Medicine. His research focuses on data-driven solutions in personalized medicine, particularly in hematological cancers and inflammatory bowel disease. He leads collaborations with clinicians on molecular and clinical data analysis, including projects like the EU-funded ARISTOTELES and the PREDICT initiative. Education: PhD in Genetics (Aarhus University, 2013), MSc in Mathematics and Statistics (2008). Research interests include clonal evolution in cancers, AI applications in clinical complexity, and mutational signature extraction. He supervises PhD students and has contributed to over 60 publications, with datasets available on platforms like Figshare. Notable collaborations involve the National Centre of Excellence for Prediction of Inflammatory Bowel Disease and EU initiatives, focusing on infrastructure for clinical data science and AI integration in healthcare.
Tung Kieu is a Tenure Track Assistant Professor in the Department of Computer Science at Aalborg University (Denmark), affiliated with The Technical Faculty of IT and Design and the Daisy Center for Data-intensive Systems. His research focuses on data engineering, time series analysis, anomaly detection, and machine learning applications in traffic forecasting and smart systems. Education: Ph.D. in Computer Science (Awarded May 2021). Research interests include time series forecasting, traffic modeling, robust autoencoder architectures for anomaly detection, and spatio-temporal data analysis. His work contributes to UN Sustainable Development Goals related to smart cities and infrastructure. Recent publications explore bias mitigation in text-video retrieval (BiMa), topology-aware traffic forecasting (TEAM), and stochastic routing in uncertain road networks. His frameworks emphasize lightweight algorithms (LightTS), causal relational learning, and continual calibration for quantized models (QCore). Collaborations involve international teams in data management and AI, with notable work on ensemble methods, explainable AI, and transfer learning in smart building systems.
Gü cin Baykal Can serves as a Research Fellow within the Department of Mathematics and Computer Science at the University of Southern Denmark. Her academic work centers on data science with specialized focus on advanced deep learning architectures and generative modeling techniques. Her research spans Deep Learning, Variational Autoencoders, and Generative Models as core specialties, extending to Machine Learning, Artificial Intelligence, and Computer Science. She develops novel methodologies to overcome critical challenges like codebook collapse in discrete variational autoencoders, significantly advancing unsupervised representation learning systems and neural network efficiency. Her publication profile features a 2024 Pattern Recognition article introducing EdVAE, an evidential discrete variational autoencoder framework. This work exemplifies her contributions to Computer Science and Artificial Intelligence, particularly in Neural Networks, Representation Learning, and Unsupervised Learning domains, demonstrating technical innovation in generative model stability. No scientific awards or honors were documented in the available information. There is no available information regarding graduate student supervision, research grant funding, or academic advising activities. Details about laboratory affiliations, research team memberships, or collaborative projects were not specified in the source material.
Sarthak Yadav is a PhD Fellow at the Department of Electronic Systems, Technical Faculty of IT and Design, Aalborg University. His research focuses on self-supervised learning for general-purpose audio representations, with affiliations to the Signals and Decoding collaboratory at the Pioneer Center for Artificial Intelligence in Copenhagen. Education: MSc(R) in Computer Science (University of Glasgow, 2022), Bachelor of Technology in Computer Science and Engineering (APJ Abdul Kalam Technological University, 2017) Yadav specializes in training large-scale deep neural networks on unlabelled audio data. His work involves developing advanced architectures like state spaces (Mamba), xLSTMs, and masked autoencoders with multi-window attention mechanisms to improve audio representation learning. These methods aim to enhance sequence modeling, emotion recognition, and time-frequency analysis. Recent publications (2024) highlight applications of selective state spaces, xLSTMs, and multi-window attention frameworks in audio processing. Earlier works focus on masked autoencoders and speech emotion recognition techniques. Yadav presented his research at major conferences including Interspeech 2024 and ICASSP 2023. He is actively engaged in collaborative projects under supervisors from Aalborg University and the Pioneer Center for Artificial Intelligence.
Nikolaj Normann Holm is a Postdoc researcher at the Department of Applied Mathematics and Computer Science, Statistics and Data Analysis at the Technical University of Denmark (DTU). His research focuses on applying data science techniques to healthcare problems, particularly in the areas of multimorbidity, chronic heart disease, and mortality prediction. His research interests center on developing and applying advanced statistical and machine learning methods to analyze complex healthcare data. Key areas include multimorbidity clustering, disease progression modeling, and mortality prediction using register-based data. His work bridges the gap between data science and medical research, creating tools that help understand complex disease patterns in population-level healthcare data. His recent publications demonstrate a strong focus on using variational autoencoders for disease clustering, analyzing co-occurring diseases in chronic heart conditions, and validating machine learning models for mortality prediction. His research consistently applies rigorous data science methodologies to address pressing healthcare challenges, particularly in the Danish healthcare system context. Dr. Holm actively participates in academic activities including conference presentations, examinations, and teaching. He has organized workshops on chronic disease selection algorithms and served as supervisor for research projects focusing on disease clustering and mortality analysis.
Rune Dodensig Kjærsgaard serves as a Consultant in the Department of Applied Mathematics and Computer Science at the Technical University of Denmark (DTU), with office location at Richard Petersens Plads, Building 324, 2800 Kgs. Lyngby. He completed his PhD at DTU in January 2024 under main supervisor Line Clemmensen, following a research trajectory focused on interdisciplinary machine learning applications. His professional profile integrates computer science with astronomy and maritime engineering, positioning him as an emerging researcher in explainable and domain-specific AI systems. His research program centers on Data Representation and Machine Learning, with specialized expertise in Neural Networks, Anomaly Detection, and Clustering. Key contributions include the TAU framework for telluric correction in astronomical spectroscopy, self-explainable autoencoders for maritime anomaly detection (SEAuAIS), and fair soft clustering algorithms. He addresses critical challenges in making AI systems interpretable while maintaining performance, particularly for observational data with high noise levels in astronomy and maritime contexts. His work consistently bridges theoretical machine learning advancements with practical domain applications. Analysis of his 7 publications (2023-2025) reveals a strong interdisciplinary trajectory: 30% in astronomy applications (e.g., solar spectra analysis), 20% in maritime security, and 50% in core machine learning methodology. Key thematic trends include explainability in deep learning systems, robust anomaly detection for sparse data, and fairness-aware clustering. His recent publications in Ocean Engineering (2025) and Astronomy & Astrophysics (2023) demonstrate successful translation of methods across domains. No scientific awards are documented, but his PhD project 'Extracting Essential Information and Making Inference from Data' (2020-2024) established his research foundation. Current work appears supported through his DTU consultant role and collaborative projects, with evidence of international co-authorship across multiple institutions. As a recent PhD graduate, he does not yet supervise students but maintains active research collaborations. Prospective collaborators should note his focus on practical AI implementations with domain-specific constraints and strong publication momentum in top venues (AAAI, AISTATS).
Jan-Matthias Braun is an Associate Professor at the Maersk Mc-Kinney Moller Institute, University of Southern Denmark, specializing in Applied AI and Data Science. His research bridges artificial intelligence, robotics, and medical device engineering. Current projects focus on explainable AI integration in colon capsule endoscopy Development of real-time FPGA-based systems for colorectal diagnostics Biomechanical modeling for adaptive orthotic devices His work emphasizes cross-disciplinary applications of machine learning in healthcare, particularly for gastrointestinal disease detection and assistive robotics. Publications demonstrate expertise in deep neural networks, hardware acceleration, and smart environment control systems. Teaching responsibilities include: Advanced cybersecurity courses Deep learning applications in epilepsy detection Mentorship in capsule endoscopy image analysis
Arnór Ingi Sigurdsson serves as a Research Fellow within the Rasmussen Group at the Novo Nordisk Foundation Center for Protein Research, University of Copenhagen, under the Faculty of Health and Medical Sciences. His work bridges computational innovation with biomedical applications, focusing on genomic data analysis and machine learning methodologies to address complex healthcare challenges. His research spans computational genomics, deep learning, and bioinformatics, with specific emphasis on genetic risk prediction for surgical outcomes, metagenomic binning techniques, and integrative models for human genomic data. Sigurdsson develops advanced neural network architectures to improve precision medicine applications, particularly in surgical risk assessment and microbiome characterization, demonstrating strong interdisciplinary collaboration across computational and clinical domains. Recent publications reveal a clear trajectory toward leveraging deep learning for genomic data interpretation, with impactful contributions in PLoS ONE and Communications Biology. His work consistently applies cutting-edge AI techniques—including adversarial autoencoders and integrative modeling—to solve concrete biomedical problems, establishing him as an emerging contributor in computational genomics. As an integral member of the Rasmussen Group, Sigurdsson collaborates extensively with cross-institutional teams at the Center for Protein Research, utilizing large-scale genomic datasets to advance personalized medicine solutions while contributing to the group's reputation in computational biology.
Jakob Nybo Nissen serves as an Assistant Professor and Affiliate Professor with the Rasmussen Group at the Faculty of Health and Medical Sciences, University of Copenhagen. His research focuses on computational biology with emphasis on metagenomics, bioinformatics, and machine learning applications for genomic data analysis. Dr. Nissen's primary research interests include: Metagenome binning and taxonomic classification Application of deep learning to genomic sequence analysis Development of computational tools for microbial community analysis Influenza virus evolution and zoonotic transmission Multi-omics data integration for disease research His recent publications demonstrate a strong focus on improving computational methods for metagenomic analysis, with several papers published in high-impact journals including Nature Communications, Nature Biotechnology, and Nature Methods. His work bridges computer science and biology, developing novel algorithms that address critical challenges in genomic data processing. Dr. Nissen is actively involved in collaborative research efforts, particularly through the Rasmussen Group, and has contributed to major initiatives like the Critical Assessment of Metagenome Interpretation. His work has practical applications in microbial ecology, disease surveillance, and personalized medicine approaches. Based at the Center for Protein Research at the University of Copenhagen, Dr. Nissen works in a vibrant research environment that integrates computational and experimental approaches to address fundamental biological questions with biomedical relevance.
