جست‌وجوی استاد و پژوهشگر

Carolina Bergelingمشاهده پروفایل

مدرس ارشد

• Brain-Computer Interfaces
• Control Engineering
• Marine Engineering Systems
• +۳ مورد دیگر

Carolina Bergeling is a Senior Lecturer in control engineering at the Department of Mathematics and Natural Sciences at Blekinge Institute of Technology (BTH), a position she has held since January 2022. Her research spans the interdisciplinary fields of Brain-Computer Interfaces, control engineering, and marine engineering systems. Dr. Bergeling's research interests focus on: Brain-Computer Interfaces and neural signal processing Control of complex systems, particularly in marine environments H-infinity optimal control theory and applications Systems engineering approaches to multi-agent and distributed systems Her recent publications demonstrate a strong focus on applying advanced control theory to Brain-Computer Interface technologies, with particular emphasis on tensor decomposition methods, domain adaptation techniques, and multi-armed bandit approaches for improving EEG signal processing and neural decoding. She also maintains an active research program in H-infinity optimal control, with contributions to theoretical foundations and practical applications in marine engineering contexts. Dr. Bergeling's scientific contributions include: Advancements in tensor decomposition techniques for transfer learning applications in BCI Novel methods for improving EEG-based decoding of auditory attention through domain adaptation Applications of multi-armed bandit theory to brain-computer interface calibration Significant contributions to H-infinity optimal control theory for various system classes She teaches courses in control engineering and robotics, and serves as a supervisor for projects in the Marine Engineering program at BTH. Her ongoing research project focuses on "Swarming technology for cooperative surface and underwater vehicles (drones)," demonstrating her commitment to applying theoretical control concepts to practical marine engineering challenges.

Foteini Liwickiمشاهده پروفایل

دانشیار

• Machine Learning
• Neuroscience
• Pattern Recognition
• +۷ مورد دیگر

Foteini Liwicki is an Associate Professor at Luleå University of Technology, Department of Computer Science, Electrical and Space Engineering, leading the Embedded Intelligent Systems LAB and the Machine Learning Focus Group – Brain Analysis since 2022. Her work bridges Artificial Intelligence and Neuroscience with applications in communication disorders, neurodegenerative conditions, and mental health. Dr. Liwicki's research focuses on multimodal brain analysis, particularly inner speech mechanisms, neurodegenerative disorders like dementia, neurodevelopmental conditions such as ADHD, and the therapeutic effects of singing on mental health. She develops computational methods for EEG-fMRI integration and interpretable machine learning approaches to understand human communication across diverse populations. Her recent publications demonstrate a strong interdisciplinary approach, combining machine learning with neuroscience, geology, and educational technology. The research trends show increasing focus on multimodal data fusion, brain-computer interfaces, and practical applications of AI in healthcare and resource management. Scientific Awards: 2023-2025: Kompetensutveckling till professor, dnr LTU-154-2023 2022: Grants for Excellent Research Projects Proposals of SRT.ai 2022 2020-2021: Ansökan juniora lovande forskare, dnr LTU-4449-2019 Dr. Liwicki actively supervises multiple PhD and Master's students across diverse research areas including brain signal analysis, inner speech detection, geological data analysis, and AI applications in healthcare. She has received significant research funding including Kempestiftelserna grants for projects on inner speech, ADHD prediction, and singing therapy for psychiatric disorders. She leads the Machine Learning Focus Group – Brain Analysis, which develops computational methods for multimodal brain analysis, and collaborates extensively with international institutions including the University of Nantes, Kyushu University, and various European research centers.

• Representation Learning
• Graph Transformer Models
• Anomaly Detection
• +۳ مورد دیگر

Mirfarid Musavian Ghazani is a Deep Learning Research Engineer at Halmstad University , affiliated with the School of Information Technology . His research focuses on representation learning for Electronic Health Records (EHR) using Graph Transformer models and anomaly detection in multivariate time series for disease outbreak surveillance. Education : MSc in Mathematics and Computer Science from Skolkovo Institute of Science and Technology (2020). Prior Experience : Led trajectory prediction projects for autonomous vehicles and indoor image localization at Skoltech's MobileRobotics Lab; worked on tensor networks and brain-computer interfaces during internships. Research Interests : Representation learning Reinforcement learning Generative models Graph neural networks Tensor decompositions Digital signal processing

• Robotics
• Computer Vision
• Human-Robot Interaction
• +۷ مورد دیگر

Mårten Björkman is a Professor at the School of Electrical Engineering and Computer Science , Royal Institute of Technology (KTH) , specializing in Robotics, Perception and Learning . His research bridges 3D computer vision with multimodal sensor fusion, including force-torque sensing, to enhance human-robot interaction. Recent work focuses on modeling sequential data for robotic control, human movement prediction, and power systems. Key research areas include: Reinforcement learning for robotic systems Human movement analysis and prediction Implicit regularization in neural networks Online learning for dynamical systems Power system control with AI 3D perception through multi-view vision His recent publications span deep learning for assembly inspection , EEG-based brain-robot interfaces , safe reinforcement learning , and multimodal motion generation . The work intersects robotics, machine learning, and human-centric system design. The Robotics, Perception and Learning division at KTH hosts his research, equipped with state-of-the-art facilities for robotic vision and human interaction studies.

Mikael Nilssonمشاهده پروفایل

مدرس ارشد

• Machine Learning
• Computer Vision
• Deep Learning
• +۴ مورد دیگر

Mikael Nilsson is a Senior Lecturer and key member of the Faculty of Engineering (LTH) at Lund University , Sweden. He is affiliated with the Centre for Mathematical Sciences and serves as Programme Director for the international master's program in Machine Learning, Systems and Control since 2019. Education : M.Sc.E.E. and Ph.D. in Applied Signal Processing (2007) from Blekinge Institute of Technology Research Focus : Developing novel Machine Learning models with emphasis on Deep Neural Network Designs Applications in Computer Vision (3D object estimation, traffic safety, radiation therapy) Applied research in Engineering Health and Natural & Artificial Cognition profile areas Recent Research Outputs (2022-2023): Medical imaging segmentation for cancer therapy (Radiation Oncology) Urban traffic surveillance systems (IEEE ITSC) 3D shape estimation from monocular vision Multi-view pose estimation via segmentation masks Yield forecasting using satellite-ground data fusion Key Collaborations : Swedish Government Agency for Innovation Systems (Vinnova) - DAIDESS project (2023-2026) Interdisciplinary work in Engineering Health and Medical Imaging Industrial collaboration with Axis Communications AB (2016-2019)

Magnus Thordsteinمشاهده پروفایل

استادیار مدعو

• Neuromodulation
• Nervous System Disorders
• Epilepsy
• +۱۱ مورد دیگر

Magnus Thordstein is an Adjunct Assistant Professor at the Department of Biomedical and Clinical Sciences within Linköping University , Sweden. His research focuses on neuromodulation techniques such as repetitive transcranial magnetic stimulation (rTMS) and transspinal direct current stimulation (tsDCS) , targeting nervous system imbalances in conditions like epilepsy and chronic pain . Thordstein collaborates with neurosurgery , neurology , and algology specialties through clinical studies.

Daniel Jönssonمشاهده پروفایل

دانشیار

• Visualization
• Machine Learning
• Medical Imaging
• +۳ مورد دیگر

Associate Professor Daniel Jönsson works at the intersection of visualization and machine learning at Linköping University's Department of Science and Technology (ITN) and Media and Information Technology (MIT) division. He leads research in transforming complex datasets into intuitive visual representations, with applications in medical imaging and neuroscience. As a core developer of the Inviwo visualization software, he emphasizes interdisciplinary collaboration across fields like AI and radiology. His work includes developing tools like VisualNeuro for brain cohort studies and exploring neural network interpretability. Research focuses on visualization techniques for high-dimensional data, including fMRI analysis and neural network exploration. Notable achievements include an honorable mention at the IEEE VIS conference (2016) for brain imaging visualization work. Collaborations with CMIV (Center for Medical Image Science and Visualization) highlight his commitment to clinical and medical research applications. Publications emphasize combining visualization with machine learning, addressing challenges in data readiness for AI projects and improving neural network analysis. His contributions span software development, algorithm design, and cross-disciplinary methodological advancements in data-driven decision-making.

Gonçalo Castelo-Brancoمشاهده پروفایل

استاد

• Epigenomics
• Transcriptomics
• Oligodendrocyte Biology
• +۷ مورد دیگر

Gonçalo Castelo-Branco is a Professor in the Department of Medical Biochemistry and Biophysics at Karolinska Institutet's Faculty of Medicine, where he leads an active research group focused on oligodendrocyte biology and epigenomics. His laboratory investigates the molecular mechanisms defining transcriptomic and epigenomic states of oligodendrocyte lineage cells in the central nervous system, particularly in the context of neuroinflammatory and demyelinating diseases like multiple sclerosis. His research employs state-of-the-art technologies including single-cell and spatial transcriptomics and epigenomics, CRISPR-based screens, and advanced computational approaches applied to rodent models of disease and human patient material. His team has made significant contributions to understanding oligodendrocyte heterogeneity, epigenetic regulation of myelination, and disease-specific oligodendrocyte states in multiple sclerosis. The publication analysis reveals a strong focus on developing and applying cutting-edge spatial and single-cell omics technologies to study neurodevelopment and neuroinflammatory diseases. His recent work (2022-2024) prominently features spatial epigenomics and multi-omic approaches that simultaneously profile chromatin accessibility, histone modifications, transcriptomes, and proteomes within the same tissue sections. Castelo-Branco is actively involved in several collaborative networks including KNIMS (The Karolinska Neuroimmunology & Multiple Sclerosis Network) and maintains multiple web resources for his datasets, most notably the OligoInternode interface which allows researchers to explore gene expression patterns in oligodendrocyte lineage cells. His research program receives substantial funding supporting the development of epigenetic-based therapies to induce regeneration/remyelination and prevent neuroinflammation in demyelinating diseases. The laboratory maintains strong international collaborations with institutions including Stockholm University, Yale University, and multiple European research centers.

Christian Balkeniusمشاهده پروفایل

استاد

• Cognitive Development
• Computational Models
• Neurophysiology
• +۷ مورد دیگر

Christian Balkenius is a Professor of Cognitive Science at Lund University's Department of Philosophy. His primary affiliation is with the Cognitive Science Department, where he leads research in computational models of cognitive development. He is based at LUX:B452 (Helgonavägen 3, Lund) and manages the Lund University Cognitive Robotics Lab. His work integrates neuroscience, robotics, and computer science to model human-like cognitive processes. Research interests focus on understanding how sensorimotor and emotional development emerge through computational modeling and robotic implementation. Notable projects include the Ikaros framework for brain-inspired robot control and studies on trust dynamics in human-robot interaction. Recent work explores time delays in social robots, haptic perception systems, and ethical aspects of AI governance. Collaborations span international teams working on topics like neurophysiological modeling and humanoid robotics. He supervises 12 documented research projects and contributes to major initiatives such as the WASP-HS program. His lab develops open platforms like the Epi humanoid robot and explores adaptive inhibition mechanisms for energy-efficient systems. Key Projects: WASP-HS, MoMa (Human-Robot Movement Analysis), Trust in Social Artefacts Labs: Lund University Cognitive Robotics Lab Grants: Swedish Foundation for Humanities and Social Sciences, Knut and Alice Wallenberg Foundation

Miguel Serras Vascoمشاهده پروفایل

پژوهشگر

• Multimodal Perception
• Reinforcement Learning
• Representation Learning
• +۴ مورد دیگر

Miguel Serras Vasco is a postdoctoral researcher at KTH Royal Institute of Technology in Stockholm, Sweden, affiliated with the Robotics, Perception and Learning (RPL) division. He holds a PhD from Instituto Superior Técnico, University of Lisbon (2023), where his work earned the Best PhD Thesis in AI in Portugal award. His research focuses on multimodal perception, reinforcement learning, and aligning artificial agents with human perception. He previously worked as an RSS Pioneer and research intern at Sony AI. Education: PhD in Artificial Intelligence, Instituto Superior Técnico, University of Lisbon (2023) Research Interests: Vasco’s work bridges robotics, neuroscience, and AI, emphasizing embodied agents that co-exist with humans. He explores representation learning, human-aligned image models, and sample-efficient reinforcement learning. His recent projects include super-human autonomous racing agents and olfactory perception modeling with transformers. Key Contributions: Vasco co-developed the GT Sophy racing agent, achieved outstanding results in visual decoding from brain activity, and proposed methods like FLoRA for preference-based RL. His work on NeuralSolver advances algorithm extrapolation in reinforcement learning. Awards: Best PhD Thesis in AI in Portugal (APPIA, 2023) Outstanding Paper Award at RLC 2024 (for autonomous racing research) Grants/Advising: Vasco advises students on multimodal and reinforcement learning topics. He actively organizes conferences like the Reinforcement Learning and Video Games Workshop (RLVG) at RLC 2025 and collaborates with institutions like INESC-ID (Lisbon). Labs/Teams: Associated with the Collaborative Autonomous Systems unit at KTH and previously with the GAIPS Lab (INESC-ID, Lisbon).

• Human-Robot Interaction
• Augmented Reality
• Mixed Reality
• +۵ مورد دیگر

Yuchong Zhang is a Postdoc Fellow at KTH Royal Institute of Technology's Division of Robotics, Perception and Learning, supervised by Prof. Danica Kragic. He completed his Ph.D. at Chalmers University of Technology (2018-2023) and holds an M.Sc. from Nanyang Technological University (2016-2017) and B.Eng. from Hangzhou Dianzi University (2012-2016). Ph.D. in Interaction Design, Chalmers University of Technology, Sweden (2018-2023) M.Sc. in Computer Science, Nanyang Technological University, Singapore (2016-2017) B.Eng. in Computer Engineering, Hangzhou Dianzi University, China (2012-2016) His research centers on human-robot interaction through human-centered design, with expertise in augmented/mixed reality , interactive AI , and affective computing . He bridges cognitive science and engineering to develop intuitive interfaces for industrial tomography and wearable robotics, emphasizing perceptual accuracy and user experience in immersive systems. Publications from 2019-2025 reveal evolving focus from industrial AR visualization (2019-2021) to brain-robot interfaces (2025) and wearable robotics (2024). Key trends include multimodal feedback in AR, EEG-based control systems, and social drone design, consistently applying human-centered methodologies across HCI, robotics, and sensory augmentation domains. He supervises master's projects in interaction design and mobile development while contributing to major initiatives like BOS (Body-centric Operating System) and ELSA (European Lighthouse on Secure AI). His work integrates hardware prototyping with user studies for industrial and assistive applications. As part of KTH's Robotics, Perception and Learning group, he collaborates on projects including TOMOCON (industrial tomography sensors) and European AI safety frameworks, leveraging his background in cross-cultural academic environments (China, Singapore, Sweden).

Bo Bernhardssonمشاهده پروفایل

استاد

• Control Engineering
• Medical Data Modeling
• Signal Analysis
• +۳ مورد دیگر

Bo Bernhardsson is a full Professor at Lund University's Department of Automatic Control within the Lund Institute of Technology (LTH). He also holds roles in ELLIIT (Linköping-Lund initiative on IT and mobile communication) and is a profile area member in Engineering Health, AI and Digitalization, and Natural and Artificial Cognition. After earning his Ph.D. in Automatic Control from Lund University in 1992 and a postdoctoral fellowship at the University of Minnesota, he returned to Lund, becoming a docent (1998) and full professor (1999). From 2001–2010, he worked at Ericsson as a mobile system design and optimization expert before resuming his academic role at Lund University. Education: Ph.D. in Automatic Control (Lund University, 1992), Docent (1998) Affiliations: ELLIIT, LTH Profile Areas (Engineering Health, AI & Digitalization), LU Profile Area (Natural and Artificial Cognition) His research focuses on EEG signal analysis , control of uncertain systems , radio-based sensing and communication , and medical data modeling , blending theoretical analysis with practical applications. His work contributes to UN Sustainable Development Goals through advancements in healthcare and communication systems. Recent research highlights include advancements in 5G NR localization, EEG-based auditory attention decoding, and transfer learning for medical signal processing. He has supervised over 37 students, including doctoral candidates like F. Heskebeck and D. Pjanić. Active in interdisciplinary collaborations, he organized workshops such as the 2021 AI Lund seminar on uncertain system modeling and contributed to projects like the 2020–2022 pandemic dynamics initiative. Bernhardsson has authored 146 publications, 19 research projects, and engaged in 41 academic activities, reflecting his leadership in both technical and educational spheres within control engineering and applied systems.

Christian Brobergerمشاهده پروفایل

استاد

• Neuroscience
• Behavioral Neuroscience
• Neuroendocrinology
• +۶ مورد دیگر

Christian Broberger is a Professor of Neurochemistry at Stockholm University's Department of Biochemistry and Biophysics. His research focuses on understanding the organization of brain circuits that control innate behaviors such as aggression, reproduction, feeding, and sleep, with particular emphasis on the hypothalamus as an evolutionary old part of the brain that interfaces with the endocrine system. Dr. Broberger's research interests span the intersection of neurochemistry, behavioral neuroscience, and neuroendocrinology. His laboratory investigates how behavior emerges from the electrical properties of neurons and the connections formed through chemical and electrical synapses. Key research areas include: Neural circuit organization controlling innate behaviors Hypothalamic regulation of aggression and social behaviors Electrical coupling through gap junctions in neural networks Neuroendocrine regulation through dopamine systems Neural mechanisms underlying reproductive behaviors Calcium-binding proteins in neuronal function His research employs a diverse range of techniques including electrophysiology, histochemistry, voltammetry, optogenetics, cell culture, and behavioral paradigms to study the central nervous system at multiple levels of organization. Recent work has particularly focused on understanding species-specific patterns of electrical coupling, neural networks controlling aggression, and dopamine regulation in neuroendocrine systems. Dr. Broberger has received recognition for his contributions to neuroscience through publications in high-impact journals including CELL, NATURE NEUROSCIENCE, JOURNAL OF NEUROSCIENCE, and E-LIFE. He supervises several PhD students and postdoctoral researchers, fostering the next generation of neuroscientists. Current members of his research group include Olga Netsyk (Researcher), Arash Hellysaz (Guest Researcher), Jimena Ferraris (Postdoc), Andrea Locarno (Postdoc), Debora Masini (Postdoc), Paul Williams (Postdoc), Roksana Khalid (PhD student), and Andriana Mantzafou (PhD student). His laboratory maintains active research projects including "Anger Management: Neuronal Network Organization, Plasticity and Sex-Specificity in Aggression" and "E Pluribus Unum: Principles and Plasticity of Electrical Coupling in a Neuronal Network," investigating fundamental questions about how social behaviors are organized at the neural circuit level.

Frida Heskebeckمشاهده پروفایل

پژوهشگر

• Brain-Computer Interfaces
• Machine Learning
• Control Engineering
• +۷ مورد دیگر

Frida Heskebeck is a Doctoral student at the Department of Automatic Control , Lund Institute of Technology , Lund University , and a member of the LTH Profile Area: AI and Digitalization . She actively contributes to the research group on EEG-based Brain-Computer Interfaces (BCI) led by Prof. Bo Bernhardsson . Research Focus: Optimization of next-generation BCI using cloud computing and individualization of real-time systems. Teaching: Delivers lectures, webinars, and lab sessions for courses like Process Control and Systems Engineering (2024), Physiological Models and Computations (2023), and Automatic Control (2021, 2020). Awards: Recipient of the Pedagogical Prize for best teaching assistant in 2021 (M-guild and W-guild) and Best Master's Thesis in 2020. Research Trends: Her recent articles focus on BCI calibration, real-time control, and cloud integration. Broad keywords include Control Engineering , Machine Learning , and Neuroscience , with sub-fields like Domain Adaptation , Signal Processing , and Online Teaching . Scientific Distinctions: Teaching assistant of the year (awarded by the M-guild) 2021 Teaching assistant of the year (awarded by the W-guild) 2021 Best Master's Thesis 2020 Advising and Collaborations: Supervision of master's theses for Tom Andersen (2021) and Johanna Wilroth (2020), where the latter received a scholarship. She also held roles in the department's board and organized seminars like the AI Lund lunch seminar in 2024.

György Kovácsمشاهده پروفایل

مدرس ارشد

• Speech and Language Technology
• Automatic Speech Recognition
• Natural Language Processing
• +۵ مورد دیگر

György Kovács is a Senior Lecturer at Luleå University of Technology, Department of Computer Science, Electrical and Space Engineering, working within the Embedded Intelligent Systems LAB. His primary research focus is on Machine Learning applications, particularly in speech and language technology. His research interests span multiple areas of speech and language processing, including: Automatic Speech Recognition across diverse conditions and languages Paralinguistic Speech Processing for emotion detection and speaker state analysis Audio event classification, including medical applications like cough sound analysis Sentiment analysis in written text, with particular interest in hateful language detection Bot detection in social media analysis Kovács has supervised numerous Master's theses since 2021, with topics ranging from accent classification and sentiment analysis to AI-generated code quality assessment. Many of these supervisions have led to co-authored publications with students. His recent publications demonstrate a strong focus on applying machine learning to diverse domains including remote sensing, healthcare technology, and natural language processing. The research shows a clear pattern of interdisciplinary work connecting machine learning with practical applications across environmental monitoring, healthcare, and social media analysis. His academic contributions include co-supervising PhD students such as Sana Al-Azzawi and Nosheen Abid, whose dissertation work on Unsupervised Curriculum Learning for Earth Observation represents significant contributions to the field. Notable publications include work on cloud detection using synthetic datasets, seagrass classification, and emotion classification using EEG in healthcare settings. Kovács also teaches courses including Introduction to Artificial Intelligence (D0032E) and Machine Learning and Pattern Recognition (D0033E), demonstrating his commitment to both research and education in the field of artificial intelligence.