جست‌وجوی استاد و پژوهشگر

• Artificial Intelligence
• Machine Learning
• Anomaly Detection
• +۶ مورد دیگر

Yuantao Fan is an Associate Senior Lecturer at Halmstad University's School of Information Technology, specializing in artificial intelligence and machine learning applications for industrial systems. His academic work bridges theoretical research with practical implementations in predictive maintenance and equipment monitoring. Dr. Fan's research focuses on Artificial Intelligence, Machine Learning, Anomaly Detection, and Data Mining , with particular emphasis on streaming data from real-world applications. His work spans equipment diagnosis and prognosis, predictive maintenance (PdM), and condition-based monitoring systems. His research integrates self-organizing models with expert knowledge to create robust diagnostic frameworks applicable to transportation systems and industrial equipment. Analysis of Dr. Fan's publication record from 2013-2025 reveals consistent specialization in predictive maintenance for transportation systems , particularly bus fleets and heavy vehicles. His work demonstrates progression from basic fault detection methods to sophisticated hybrid approaches combining physics-based models with deep learning. Recent publications increasingly address explainability in predictive maintenance systems and applications in healthcare analytics. Dr. Fan actively contributes to academic instruction as course responsible and examiner for Databases, Introduction to Linux and Python, and Linux administration system courses. He also teaches Artificial Intelligence, Data Mining, Perspectives on Computer Science and Engineering, Machine Learning for Predictive Maintenance, and AI Implementation courses. His technical expertise spans multiple domains including automotive systems diagnostics, battery health monitoring, acoustic signal processing, and healthcare prediction models. Dr. Fan's work demonstrates strong industry collaboration, particularly with Volvo and city bus fleet operators, translating academic research into practical industrial applications.

• Machine Learning
• Artificial Intelligence
• Cybersecurity
• +۴ مورد دیگر

Zahra Taghiyarrenani is a postdoctoral researcher at Halmstad University , affiliated with the School of Information Technology and the IT - Computer Department . Her work bridges theoretical advancements in machine learning with practical applications in industrial and cybersecurity domains. Education : PhD in Machine Learning (2024, Halmstad University), Licentiate Thesis on Multi-Domain Learning (2022) Her research focuses on domain adaptation , federated learning , and explainable AI , with emphasis on handling data scarcity and heterogeneity. Key projects include fault identification in industrial systems, intrusion detection, and physics-informed models for diagnostics. Her publications highlight trends in cross-domain learning , combining privacy-preserving AI with edge computing , and addressing data efficiency through few-shot/supervised methods . Recent work explores Industry 5.0 applications of Explainable AI. Projects: EVE : Extending vehicle lifespan in electromobility Federated Learning for Well-being : Privacy and fairness in AI FeelAI : Edge-based predictive logistics models

Selpi Selpiمشاهده پروفایل

پژوهشگر

• Data-centric AI
• Multimodal Learning
• Unsupervised Learning
• +۶ مورد دیگر

Selpi Selpi is a Researcher at the Department of Data Science and AI , Chalmers University of Technology. They lead Work Package 3 (Methodologies for Assessment) in the EU-funded PANACEA project , focusing on fit-to-drive assessments for professional drivers through data fusion and impairment detection. Supervision: Main advisor to doctoral students Amer Mustajbasic (2023-present) and Mengyu Huang (2024-present). Research Interests: Data-centric AI, multimodal learning, unsupervised learning, and interpretable AI applied to autonomous driving and traffic safety. Key contributions include algorithms for driver behavior analysis in mixed traffic, BEV data fusion techniques, and scenario-based risk assessment frameworks. Publications from 2025–2017 span journals like IEEE Transactions on Intelligent Transportation Systems and conference proceedings at ECML PKDD.

• Optical Networking
• Machine Learning in Network Automation
• Physical Layer Security
• +۳ مورد دیگر

Carlos Natalino Da Silva is a Researcher at Chalmers University of Technology's Optical Networks Unit , focusing on network automation and machine learning applications in optical network design and security. His work addresses resource efficiency (e.g., spectrum optimization), physical layer security , and 6G readiness , with involvement in EU and Brazil-funded projects. He has also contributed to computer programming education in Brazil and Sweden. Research Interests : Machine learning for optical networks Network automation and programmability Physical layer security 6G network readiness Distributed computing optimization Recent Article Trends : His 2025-2024 publications emphasize ML for QoT estimation , state-of-polarization analysis , hybrid FSO-THz for 6G , and DRL-assisted resource allocation , reflecting a focus on convergence between AI, security, and next-gen optical systems. Projects & Collaborations : Current initiatives include Resilient Remote Environment Emulation (2025-2025, ARC-funded), ECO-eNET (2024-2028, EU), and EMPOWER - 6G (2024-2027). Past projects span PHOTONIC HARDWARE (VR-funded), TeraFlow (EU), and ANIARA (VINNOVA).

• Bioinformatics and Computational Biology
• Cancer Precision Medicine
• Computational Pathology
• +۵ مورد دیگر

Mattias Rantalainen is a Senior Lecturer and Docent at Karolinska Institutet's Department of Medical Epidemiology and Biostatistics, where he leads the Predictive Medicine research group. His work focuses on applying statistical machine learning, artificial intelligence, and big data analytics to medical research, with particular emphasis on computational pathology and cancer precision medicine. The research group maintains over 300,000 whole slide images for population-based studies, primarily focused on breast, prostate, and colorectal cancer. Dr. Rantalainen completed his PhD at Imperial College London developing multivariate pattern recognition methods with applications in metabonomics. He previously held a research fellowship (2009-2013) with joint affiliation at the Department of Statistics and the Wellcome Trust Centre for Human Genetics at the University of Oxford, where he was awarded the MRC Centenary Early Career Award (2012-2013) and a Medical Research Council Special Training Fellowship in Biomedical Informatics (2009-2012). He holds an undergraduate degree in Engineering Biology (combined BSc/MSc) from Umeå University in Sweden. His research interests span computational pathology, cancer precision medicine, and AI-driven medical research. The Predictive Medicine group develops and applies AI and machine learning methodologies for predictive modeling in biomedical applications. Their mission is to transform large biomedical datasets into clinically relevant predictions at the individual level, with a particular focus on precision pathology applications where the goal is to predict patient outcomes. Their work integrates comprehensive molecular profiling (DNA- and RNA-sequencing), clinical information, and medical imaging data. Analysis of his recent publications reveals a strong trend toward developing and validating deep learning models in computational pathology, particularly for breast cancer applications. His work focuses on risk stratification, histological grading, and gene expression prediction from histopathology images. There's a clear progression from method development to clinical validation and implementation, with increasing emphasis on real-world applicability and comparison with established clinical assays. His research bridges the gap between computational methodology and clinical practice in cancer diagnostics. MRC Centenary Early Career Award (2012-2013) Medical Research Council (MRC) Special Training Fellowship in Biomedical Informatics (2009-2012) Dr. Rantalainen serves as main supervisor for PhD students Philippe Weitz and Abhinav Sharma, and as co-supervisor for several other doctoral candidates including Dusan Rasic, Sandra Kristiane Sinius Pouplier, and Tewodros Yalew. He coordinates the Swedish AI Precision Pathology (SwAIPP) consortium, which focuses on translation and implementation of AI-based pathology. His group has received significant funding, including a recent 120 million SEK grant to the Department of Medical Epidemiology and Biostatistics from Swedish funding agencies. The Predictive Medicine group operates within the Department of Medical Epidemiology and Biostatistics at Karolinska Institutet, coordinating several national and international initiatives including the CHIMES study (www.chimestudy.se), ABCAP (www.abcap.org), and the Swedish AI Precision Pathology consortium (www.swaipp.org). The group has developed numerous AI-based tools that improve cancer diagnosis and risk prediction, with several projects advancing toward clinical implementation as regulatory-approved medical devices. Their work represents a significant contribution to the field of precision pathology and AI-driven cancer diagnostics.

Ellen Tolestam Heymanمشاهده پروفایل

پژوهشگر

• Emergency Medicine
• Artificial Intelligence
• Machine Learning
• +۶ مورد دیگر

Ellen Tolestam Heyman is a MD PhD Student Researcher at Lund University's Faculty of Medicine, Department of Emergency Medicine. She works clinically as a resident physician in the emergency department at Halland Hospital Varberg while conducting AI-focused research within the interdisciplinary AIR Lund program. Her work explores AI applications for improving diagnostic accuracy, mortality prediction, and resource allocation in emergency care. Her research interests include: AI and machine learning for emergency medicine diagnostics Resource management optimization in acute care settings Clinical decision support systems Integration of ethical AI in healthcare Research trends show focus on dyspnea diagnosis, triage efficiency, and predictive analytics using cross-sectional studies and deep learning models. Her work aligns with UN Sustainable Development Goals for healthcare quality and accessibility. Scientific awards include multiple grants for AI-supported diagnostic systems (2021–2023). She actively contributes to academic discourse through presentations on AI's future in emergency medicine.

Anders Eklundمشاهده پروفایل

دانشیار

• Medical Image Analysis
• Machine Learning
• Medical Informatics
• +۳ مورد دیگر

Anders Eklund is a Senior Associate Professor at Linköping University, affiliated with both the Department of Biomedical Engineering (IMT) and the Department of Computer and Information Science (IDA). He holds roles in the Center for Medical Image Science and Visualization (CMIV), focusing on developing advanced methods for medical image analysis, including applications in pediatric brain tumor classification, synthetic image generation, and federated learning frameworks. His research bridges biomedical engineering, artificial intelligence, and data science to address clinical challenges such as improving diagnostic accuracy and reducing healthcare resource bottlenecks. Education: Master of Science (2007), PhD in Medical Informatics (2012), Postdoc at Virginia Tech (2012–2014), Docent (2016), Associate Professor (2021). Research Interests: Medical image processing, deep learning for healthcare, federated learning for sensitive data, synthetic medical image generation, and statistical validation of neuroimaging techniques. Notable contributions include exposing flaws in fMRI analysis software and advancing AI-driven solutions for radiation treatment planning. Publications: Recent work emphasizes deep learning applications in medical imaging, including tumor classification, federated learning for privacy-preserving models, and synthetic image techniques to address data scarcity. His articles reflect a focus on interdisciplinary solutions for healthcare challenges, such as reducing queues post-pandemic through automated brain image analysis. Grants & Advising: Secured a 3.6M SEK grant from the Swedish Research Council (2016). Supervised numerous PhD students, including main supervision of Xuan Gu (2019) and co-supervision of Per Sidén (2020). Active in training the next generation of biomedical engineers and AI researchers. Labs & Collaborations: Leads projects within CMIV and collaborates across departments at Linköping University. Involved in initiatives like the ASSIST project, which aims to automate brain image analysis to free clinician time.

Carl Westinمشاهده پروفایل

استادیار

• Human Factors
• Human-Automation Collaboration
• Safety-Critical Systems
• +۳ مورد دیگر

Carl Westin is an Assistant Professor at Linköping University's Department of Science and Technology (ITN), within the Media and Information Technology (MIT) division. He holds a PhD in Human Factors from Delft University of Technology (2017), an MSc in Applied Ergonomics from the University of Nottingham (2012), and a Commercial Pilot diploma from Lund University (2006). His research focuses on enhancing human-automation collaboration in safety-critical environments like aviation, maritime transport, and air traffic control. Key themes include automation transparency, personalized decision support, and the application of eye-tracking and visual analytics to improve system design and user understanding. Westin's work emphasizes designing automation that aligns with human cognitive strategies (e.g., 'strategic conformance') to foster trust and efficiency. He leads projects such as the EU-funded 'Explain Yourself' initiative, which explores automation transparency for end-users. His research bridges academia and industry, addressing challenges in air traffic management, maritime piloting, and unmanned aerial systems. Collaborations include partnerships with organizations like the Swedish Transport Agency and the European Union Aviation Safety Agency (EASA). Education: PhD in Human Factors, Delft University of Technology (2017) MSc in Applied Ergonomics, University of Nottingham (2012) Air Traffic Pilot Diploma, Lund University (2006) Key Projects: Explain Yourself: Designing Automation Transparency for End Users (EU Horizon 2020) RESKILL: Interactive Visualization for Self-Explanatory Automation DiTA Digital Tower Assistant for Remote Air Traffic Control Labs/Teams: Member of the Media and Information Technology (MIT) research group, focusing on visual analytics and human-automation systems. His publications span journals like Cognition, Technology & Work and conferences like IEEE Visualization, with a focus on empirical studies of human-automation interaction in safety-critical domains. Recent work explores AI transparency, visual analytics for decision support, and guidelines for ethical AI in air traffic management.

Björn Forsbergمشاهده پروفایل

استادیار

• Structural Bioinformatics
• Cryo-Electron Microscopy (Cryo-EM)
• Computational Biology
• +۷ مورد دیگر

Björn Forsberg is an Assistant Professor in the Department of Physics, Chemistry and Biology (IFM) at Linköping University, where he leads a research group in structural bioinformatics. He is affiliated with SciLifeLab Linköping and the National Supercomputer Centre (NSC), and is part of the Wallenberg National Program for Data-Driven Life Science (DDLS), supported by the Knut and Alice Wallenberg Foundation. His work bridges computational science and molecular biology, focusing on the development of novel methods for analyzing cryo-electron microscopy (cryo-EM) data. His research centers on understanding molecular life through data-driven approaches. He develops computational tools to analyze ensemble cryo-EM data, using spatial filtering and local correlation metrics to identify sources of structural variation and attribute them to biological mechanisms. His lab leverages high-performance computing resources, including the Berzelius supercomputer, to process large-scale datasets and improve the resolution and interpretability of molecular models. This work has broad implications for understanding diseases like Alzheimer's and for drug discovery. The recent publications highlight a strong trend in advancing cryo-EM methodology, particularly through software development (e.g., RELION) and the integration of machine learning and GPU computing. His work spans fungal metabolism, ion channel dynamics, chloroplast ribosomes, and foundational algorithmic improvements in 3D reconstruction. The research combines structural biology, bioinformatics, and computational physics to extract biological meaning from complex data. Scientific Awards and Recognition: Selected for the SciLifeLab and Wallenberg National Program for Data-Driven Life Science (DDLS) Supported by the Knut and Alice Wallenberg Foundation through DDLS and the PALS (Program for Academic Leaders in Life Science) network Björn Forsberg is actively building his research team, advising PhD and master’s students, and seeking postdoctoral researchers with backgrounds in computational biology, computer science, or related fields. His lab collaborates with leading experts in structural biology and uses national research infrastructures to push the boundaries of data-driven life science. He has no listed formal grants yet, but his program is funded through major foundation support. His research is conducted at the intersection of the Department of Physics, Chemistry and Biology (IFM), SciLifeLab Linköping, and the National Supercomputer Centre (NSC), forming a multidisciplinary environment for innovation in computational structural biology.

Mirjam Palosaari Eladhariمشاهده پروفایل

دانشیار

• AI-based Game Design
• Interactive Digital Narratives
• Co-creation in Games
• +۷ مورد دیگر

Mirjam Palosaari Eladhari is an Associate Professor (Docent) at the Department of Computer and Systems Sciences, Stockholm University. Her work bridges AI-based game design, interactive narratives, and co-creation, focusing on meaningful play experiences for mental health and cultural representation. Teaching: Game design and research methods Research: Interactive digital narratives, assistive technology, queer representation in games Projects: EU COST Action INDCOR, Sweden’s Female-Forward Creative Industries, Autism support platform Mirjam leads the Distributed Immersive Participation research group, exploring participation in physical and virtual societies. She contributes to organizations like Higher Education Video Game Alliance and Society for the Advancement of the Study of Digital Games . Her practical work includes games under the label Otter Play and digital art projects.

Meriem Beloucifمشاهده پروفایل

استادیار

• Natural Language Processing
• Machine Translation
• Lexical Semantics
• +۳ مورد دیگر

Meriem Beloucif serves as an Assistant Professor in Computational Linguistics at Uppsala University's Department of Linguistics and Philology, focusing on neural machine translation and lexical semantics for low-resource languages. Her work bridges theoretical linguistics and practical NLP applications, particularly for underrepresented language communities. Education: PhD in Machine Translation from HKUST (Hong Kong) Prior research appointments at Hamburg University (Comparative QA) and Copenhagen University (Semantic Parsing) Research Interests: Core expertise in low-resource language processing for African and Indigenous languages Specialization in sentiment analysis benchmarks (AfriSenti) and semantic role labeling Investigation of pre-trained language model capabilities through probing techniques Development of preprocessing strategies for challenging languages like Inuktitut Her publication trajectory (2021-2023) reveals concentrated efforts in creating evaluation frameworks for African languages, advancing cross-lingual transfer methods, and analyzing semantic compositionality in transformers. Key contributions include standardized datasets for semantic relatedness and novel approaches to zero-shot sentiment classification in Nigerian Pidgin. Collaborative work with researchers like Shamsuddeen Muhammad and Micaella Bruton demonstrates active mentorship in computational linguistics projects. While specific grant details aren't documented, her leadership in SemEval shared tasks indicates significant community engagement in NLP evaluation standards.

• Signal Processing
• Machine Learning
• Statistical Signal Processing
• +۱۱ مورد دیگر

Saikat Chatterjee is a Professor in the Department of Information Science and Engineering at the School of Electrical Engineering and Computer Science, Royal Institute of Technology (KTH). He is also a Fellow of Digital Futures and maintains visiting researcher positions at Karolinska Institute, Karolinska Hospital (specializing in 'AI for Health Care'), and Oslo University Hospital in Norway. His primary research interests span Signal Processing and Machine Learning, with specific focus on signal modeling (sparsity, compressive sensing, dynamical systems), statistical signal processing, statistical machine learning, deep learning, speech/audio/image processing, medical data analytics, life science data analysis, perception for autonomous systems, distributed machine learning, and explainable AI (XAI). He particularly emphasizes explainable machine learning, having a strong background in signal processing and statistical machine learning, with growing passion for medical data analysis due to its societal importance. SSF - Swedish Foundation for Strategic Research Region Stockholm European Union Digital Futures Vinnova WASP Companies: Ericsson, Scania, Saab Professor Chatterjee is actively involved in teaching, serving as examiner and course responsible for various degree projects and courses including Machine Learning and Data Science, Pattern Recognition and Machine Learning, and Speech and Audio Processing. His research group has produced significant work across multiple domains, with notable publications in Bioinformatics and smart city applications, demonstrating the breadth of his research impact from healthcare to urban systems.

• Optical Networks
• Network Automation
• Spectrally-Spatially Flexible Optical Networks
• +۲ مورد دیگر

Piotr Lechowicz is a postdoctoral researcher at the Optical Networks (ON) Unit within the Department of Electrical Engineering at Chalmers University of Technology . He holds an M.Sc. (2016) and Ph.D. (2019) in Information and Communications Technology from the Wrocław University of Science and Technology in Poland. A member of IEEE since 2020, his work focuses on the modeling and optimization of optical networks, particularly in network automation, spectrally-spatially flexible optical networks, and network fragmentation. Education: M.Sc. in Information and Communications Technology (2016), Wrocław University of Science and Technology Ph.D. in Technical Information and Communications Technology (2019), Wrocław University of Science and Technology Research Interests: Lechowicz specializes in optical network modeling, optimization, and automation. His work addresses challenges in spectrally-spatially flexible and elastic optical networks, with a focus on time-varying traffic, resource allocation, and network fragmentation. He integrates machine learning techniques, including transfer learning and graph-based methods, to enhance network performance and reliability. Publications and Collaborations: He has co-authored 35 publications (10 JCR-indexed, 25 conference papers), often collaborating with researchers like Carlos Natalino Da Silva, Aleksandra Knapinska, and Paolo Monti. His projects involve time-varying traffic analysis, energy efficiency in multilayer networks, and explainable AI for network optimization. Professional Contributions: Lechowicz has reviewed over 60 scientific papers and participated in six projects funded by the Polish National Science Center and National Center for Research and Development. His methodological innovations include the Traffic Weaver tool for generating semi-synthetic network traffic data.

• Machine Learning
• Visual Analytics
• Explainable AI
• +۷ مورد دیگر

Juhee Bae is a Senior Lecturer in the Department of Information Technology at the University of Skövde, Sweden. She is affiliated with the AI research group, focusing on machine learning, visual analytics, and explainable AI. Her work bridges research and education, with courses in advanced data science and experience in teaching coordination. Ph.D. in Computer Science, North Carolina State University Merited Teaching Award (2023) Mobility Grant for Belgian University Collaboration (2020) Her research spans machine learning , visual analytics , and explainable AI , with applications in Steel industry process optimization Climate-adaptive water management Migration intention forecasting Smart production logistics Wearable biosensor analysis Recent publications highlight predictive models for weather-driven migration, causal discovery frameworks, and interactive data mining techniques. She contributes to editorial boards and conference organization. Juhee Bae serves as course coordinator for Explainable AI and has been active in international collaborations. Scientific awards include 2023 Merited Teaching Award 2020 Mobility Grant Her projects STRATUS (AI for climate adaptation), INSITE-X (steel industry AI), and Understanding Human Migration demonstrate practical AI applications. She works with interdisciplinary teams and has presented talks on predictive machine learning and explainable AI.

• Robotics
• Artificial Intelligence
• Human-Robot Interaction
• +۶ مورد دیگر

Thomas Hellström is a Professor at the Department of Computing Science at Umeå University and is also affiliated as a professor at the Centre for Transdiciplinary AI. He leads the Intelligent Robotics group, focusing on the application of artificial intelligence for developing robots for social and industrial applications, with a particular emphasis on Human-Robot Interaction (HRI). His research spans multiple domains including social robotics, field robotics, and robot ethics. Hellström's research interests center around making robots more understandable and effective in human environments. His work in Human-Robot Interaction explores how robots can communicate their intentions and actions clearly to humans, while his field robotics research focuses on unmanned forest vehicles and agricultural robotics. He has made significant contributions to robot ethics, particularly regarding military applications of robotics, and has published extensively on bias in machine learning. His approach combines theoretical frameworks with practical implementations, often resulting in tangible robotics systems. The analysis of Hellström's recent publications reveals a consistent focus on making robotic systems more transparent, understandable, and socially competent. His work increasingly integrates multiple modalities of interaction, combines cognitive models with practical robotics, and addresses the ethical implications of deploying AI systems in real-world contexts. There's a clear trajectory toward more sophisticated human-robot collaboration frameworks that respect social norms while maintaining technical effectiveness. Hellström has successfully supervised numerous PhD students including Michele Persiani, Ahmad Ostovar, Benjamin Fonooni, Mostafa Pordel, and Ola Ringdahl, while also serving as co-supervisor for several others. His research has been generously funded through multiple EU projects including INTRO (2010-2014), SOCRATES (2016-2020), CROPS, and SWEEPER, along with grants from Vetenskapsrådet, VINNOVA, and various foundations. At Umeå University, Hellström leads the Intelligent Robotics group which maintains strong connections with both academic and industrial partners. The group has developed notable systems including an intelligent rollator for stroke patients and harvesting robots for agricultural applications. Their work often bridges theoretical AI research with practical implementations in real-world environments, particularly in healthcare and agriculture.