A5020376157- Machine Learning in Healthcare
- Sepsis Diagnosis and Treatment
- Respiratory Support and Mechanisms
- Artificial Intelligence in Healthcare and Education
- COVID-19 diagnosis using AI
- Traffic Prediction and Management Techniques
- Human Mobility and Location-Based Analysis
- Mobile Agent-Based Network Management
- Frailty in Older Adults
- Data Stream Mining Techniques
- Distributed and Parallel Computing Systems
- Time Series Analysis and Forecasting
- Face and Expression Recognition
- Vehicular Ad Hoc Networks (VANETs)
- Intensive Care Unit Cognitive Disorders
- Advanced Data Storage Technologies
- Parallel Computing and Optimization Techniques
- Service-Oriented Architecture and Web Services
- AI in cancer detection
- Imbalanced Data Classification Techniques
- Software System Performance and Reliability
University of Iceland
2021-2023
Forschungszentrum Jülich
2021
Introduction The acute respiratory distress syndrome (ARDS) is a highly relevant entity in critical care with mortality rates of 40%. Despite extensive scientific efforts, outcome-relevant therapeutic measures are still insufficiently practised at the bedside. Thus, there clear need to adhere early diagnosis and sufficient therapy ARDS, assuring lower multiple organ failure. Methods analysis In this quality improvement strategy (QIS), decision support system as mobile application (ASIC app),...
We observe a continuously increased use of Deep Learning (DL) as specific type Machine (ML) for data-intensive problems (i.e., 'big data') that requires powerful computing resources with equally increasing performance. Consequently, innovative heterogeneous High-Performance Computing (HPC) systems based on multi-core CPUs and many-core GPUs require an architectural design addresses end user communities' requirements take advantage ML DL. Still the workloads communities simulation sciences...
Acute Respiratory Distress Syndrome (ARDS) is a condition that endangers the lives of many Intensive Care Unit patients through gradual reduction lung function. Due to its heterogeneity, this has been difficult diagnose and treat, although it subject continuous research, leading development several tools for modeling disease progression on one hand, guidelines diagnosis other, mainly "Berlin Definition". This paper describes deep learning-based surrogate model such tool ARDS onset in virtual...
An increasing number of data science approaches that take advantage deep learning in computational medicine and biomedical engineering require parallel scalable algorithms using High-Performance Computing systems. Especially methods for analysing clinical datasets consist multivariate time series can benefit from when applying computing-intensive Recurrent Neural Networks. This paper proposes a dynamic platform consisting modular systems accelerators innovative Deep Learning to speed-up...
The COVID-19 pandemic shed light on the need for quick diagnosis tools in healthcare, leading to development of several algorithmic models disease detection. Though these are relatively easy build, their training requires a lot data, storage, and resources, which may not be available use by medical institutions or could beyond skillset people who most tools. This paper describes data analysis machine learning platform that takes advantage high-performance computing infrastructure support...
Acute Respiratory Distress Syndrome (ARDS), also known as noncardiogenic pulmonary edema, is a severe condition that affects around one in ten-thousand people every year with life-threatening consequences. Its pathophysiology characterized by bronchoalveolar injury and alveolar collapse (i.e., atelectasis), whereby its patient diagnosis based on the so-called 'Berlin Definition'. One common practice Intensive Care Units (ICUs) to use lung recruitment manoeuvres (RMs) ARDS open up unstable,...
The European Center of Excellence in Exascale Computing "Research on AI- and Simulation-Based Engineering at Exascale" (CoE RAISE) is a project funded by the Commission. One its central goals to develop Unique AI Framework (UAIF) that simplifies development models cutting-edge supercomputers. However, those supercomputers' High-Performance (HPC) environments require knowledge many low-level modules all need work together different software versions (e.g., TensorFlow, Python, NCCL, PyTorch)...
Given the Covid-19 pandemic, retail industry shifts many business models to enable more online purchases that produce large transaction data quantities (i.e., big data). Data science methods infer seasonal trends about products from this and spikes in purchases, effectiveness of advertising campaigns, or brand loyalty but require extensive processing power leveraging High-Performance Computing deal with datasets. This paper proposes an Computing-based expert system architectural design...