جست‌وجوی استاد و پژوهشگر

Anne de Hondمشاهده پروفایل

استادیار

• Artificial Intelligence in Healthcare
• Machine Learning
• Clinical Decision Support Systems
• +۳ مورد دیگر

Anne de Hond is an Assistant Professor in the Data Science Program at UMC Utrecht’s Julius Center, specializing in the responsible development, validation, and implementation of AI algorithms in healthcare. Her work bridges machine learning and clinical decision-making, with applications in mortality prediction, depression risk assessment, and ICU workflow optimization. Her research focuses on enhancing the reliability and fairness of AI models in clinical settings. Key projects include predicting hospital admissions at emergency departments, assessing depression risk in oncology patients, and analyzing the practical implementation of AI software in collaboration with startups. She also explores explainability and validation frameworks for emerging technologies like large language models. Anne’s recent publications span Predictive modeling for hip fracture mortality Frailty assessment in COVID-19 Workflow integration of AI in ICU Comorbidity index limitations Class imbalance in ML models Shortness of breath triage systems She is affiliated with the Julius Center at UMC Utrecht and previously conducted PhD research at Leiden UMC’s CAIRELab, combining a master’s in econometrics with clinical AI applications.

• Artificial Intelligence
• Data Mining
• Process Mining
• +۵ مورد دیگر

Faiza Allah Bukhsh is an Associate Professor specializing in Artificial Intelligence, Data Mining, Process Mining, Health Informatics, Cybersecurity, and Ethical AI. Her work bridges technical innovation with societal impact, particularly in healthcare systems analysis, telecommunications resilience, and ethical data governance. Digital Society Institute TechMed Centre Datamanagement & Biometrics Her research focuses on Explainable AI , Process Mining , and Privacy Assurance in healthcare systems, with recent work on AI music perception, sepsis treatment analysis, and privacy-utility trade-offs. Key article trends include: AI in music and creative domains Process Mining for healthcare insights Explainable Machine Learning workflows Privacy-preserving analytics Telcom infrastructure resilience

Marcos Machadoمشاهده پروفایل

استادیار

• Artificial Intelligence
• Data Science
• Machine Learning
• +۶ مورد دیگر

Marcos Machado is an Assistant Professor in Industrial Engineering & Business Information Systems, focusing on Artificial Intelligence, Machine Learning, and Sustainable Industry applications. His research spans Financial Technology (e.g., credit risk assessment, fraud detection), Energy Efficiency in industrial contexts, and Circular Economy strategies for SMEs. Current research trends highlight hybrid AI models integrating traditional time series analysis Key domains: Retail banking, steel industry optimization, commodity price modeling Contributions to UN SDGs: Climate Action, Responsible Consumption, Industry Innovation Recent activities include international collaborations and presentations on circular economy frameworks.

Sandjai Bhulaiمشاهده پروفایل

پژوهشگر

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

Dr. Sandjai Bhulai is a Researcher at Centrum Wiskunde & Informatica (CWI) in Amsterdam, The Netherlands, and affiliated with Vrije Universiteit Amsterdam. He works in the Stochastics department within the Faculty of Science, focusing on applying machine learning and optimization techniques to solve complex real-world problems across diverse domains including telecommunications, mental health crisis intervention, and operations research. His research spans multiple critical areas of applied mathematics and computer science: Development of novel machine learning evaluation frameworks (Dutch Draw, Dutch Scaler) Optimization algorithms for facility location and supply chain problems Telecommunications signal processing using deep learning Mental health applications, particularly suicide prevention helpline analysis Natural language processing for conversation analysis in crisis intervention Dr. Bhulai's recent work demonstrates exceptional interdisciplinary impact. His Dutch Draw framework provides a universal baseline for binary classification problems that has been adopted across multiple research communities. His mental health research has directly influenced suicide prevention practices through machine learning analysis of helpline conversations, identifying specific counselor interventions that improve outcomes. In telecommunications, he's developed neural network approaches that simultaneously handle multiple modulation schemes, improving efficiency in wireless communications. His scientific contributions appear in leading venues including: Computers and Operations Research Journal of Classification IEEE Open Journal of the Communications Society JMIR Mental Health Journal of Applied Probability Dr. Bhulai maintains strong collaborative relationships with researchers across institutions, particularly with Rob van der Mei at CWI. He has secured funding for impactful projects including the collaboration between Stichting 113 Suicide Prevention and CWI, which applies machine learning to improve crisis intervention services. His work exemplifies how theoretical advances in machine learning can address critical societal challenges.

Noura Al Moubayedمشاهده پروفایل

دانشیار

• Explainable Machine Learning
• Natural Language Processing
• Optimisation
• +۶ مورد دیگر

Dr. Noura Al Moubayed serves as an Associate Professor in the Department of Computer Science at Durham University, specializing in Explainable Machine Learning, Natural Language Processing, and Optimisation for high-dimensional data challenges. Education PhD from Robert Gordon University Post-doctoral positions at University of Glasgow and Durham University Research Focus Her work develops machine learning solutions for healthcare, social signal processing, cyber-security, and Brain-Computer Interfaces, specifically targeting noisy and imbalanced datasets through advanced NLP and optimization techniques. Current projects integrate deep learning with explainability frameworks to enhance real-world applicability. Publication Trends Recent publications (2020-2022) demonstrate consistent focus on improving question answering systems via bilinear pooling and paraphrasing techniques, alongside novel deep learning approaches for probabilistic topic modeling. These works bridge computer vision, NLP, and multimodal learning to address data imbalance challenges across healthcare and social computing domains. Academic Service PeerJ Computer Science Editorial Board Member 335 authorship points and 30 reviewer points on PeerJ platform