A5008220787- Distributed and Parallel Computing Systems
- Scientific Computing and Data Management
- Advanced Data Storage Technologies
- Remote-Sensing Image Classification
- Cloud Computing and Resource Management
- Remote Sensing in Agriculture
- Parallel Computing and Optimization Techniques
- Quantum Computing Algorithms and Architecture
- Remote Sensing and Land Use
- Advanced Image and Video Retrieval Techniques
- Advanced Neural Network Applications
- Quantum Information and Cryptography
- Distributed systems and fault tolerance
- Machine Learning in Healthcare
- Advanced Clustering Algorithms Research
- Machine Learning and Data Classification
- Neural Networks and Applications
- Advanced Image Fusion Techniques
- Artificial Intelligence in Healthcare and Education
- Big Data and Business Intelligence
- Time Series Analysis and Forecasting
- Big Data Technologies and Applications
- Service-Oriented Architecture and Web Services
- Peer-to-Peer Network Technologies
- Energy Load and Power Forecasting
Forschungszentrum Jülich
2016-2025
University of Iceland
2016-2025
Karlsruhe Institute of Technology
2024
University of Twente
2023
University of Trento
2021-2022
RWTH Aachen University
2010-2022
Stadtwerke Jülich (Germany)
2021-2022
Obuda University
2022
Automated Precision (United States)
2022
University of Zagreb
2018
Objective The attitudes about the usage of artificial intelligence in healthcare are controversial. Unlike perception professionals, patients and their companions have been less interest so far. In this study, we aimed to investigate among highly relevant group along with influence digital affinity sociodemographic factors. Methods We conducted a cross-sectional study using paper-based questionnaire at German tertiary referral hospital from December 2019 February 2020. consisted three...
Summary Introduction: This article is part of the Focus Theme Methods Information in Medicine on German Medical Informatics Initiative. “Smart Technology for Healthcare (SMITH)” one four consortia funded by Initiative (MI-I) to create an alliance universities, university hospitals, research institutions and IT companies. SMITH’s goals are establish Data Integration Centers (DICs) at each SMITH partner hospital implement use cases which demonstrate usefulness approach. Objectives: To give...
The wide variety of scientific user communities work with data since many years and thus have already a infrastructures in production today. aim this paper is not to create one new general architecture that would fail be adopted by each any individual community. Instead contribution aims design reference model abstract entities able federate existing concrete under umbrella. A an framework for understanding significant relationships between them helps understand when comparing terms...
Owing to the recent development of sensor resolutions onboard different Earth observation platforms, remote sensing is an important source information for mapping and monitoring natural man-made land covers. Of particular importance increasing amounts available hyperspectral data originating from airborne satellite sensors such as AVIRIS, HyMap, Hyperion with very high spectral resolution (i.e., number channels) containing rich a wide range applications. A relevant example separation types...
Background The increasing development of artificial intelligence (AI) systems in medicine driven by researchers and entrepreneurs goes along with enormous expectations for medical care advancement. AI might change the clinical practice physicians from almost all disciplines most areas health care. While are high, practical implementations still scarce Germany. Moreover, physicians’ requirements their opinion on usage anonymized patient data biomedical research have not been investigated...
In recent years, the development of quantum annealers has enabled experimental demonstrations and increased research interest in applications annealing, such as machine learning particular for popular Support Vector Machine (SVM). Several versions SVM have been proposed, annealing shown to be effective them. Extensions multiclass problems also made, which consist an ensemble multiple binary classifiers. This work proposes a novel formulation direct classification based on called Quantum...
Clustering algorithms in the field of data-mining are used to aggregate similar objects into common groups. One best-known these is called DBSCAN. Its distinct design enables search for an apriori unknown number arbitrarily shaped clusters, and at same time allows filter out noise. Due its sequential formulation, parallelization DBSCAN renders a challenge. In this paper we present new parallel approach which call HPDBSCAN. It employs three major techniques order break sequentiality, empower...
Support Vector Machine (SVM) is a popular supervised Learning (ML) method that widely used for classification and regression problems. Recently, to train SVMs on D-Wave 2000Q Quantum Annealer (QA) was proposed binary of some biological data. First, ensembles weak quantum are generated by training each classifier disjoint subset can be fit into the QA. Then, computed solutions fused making predictions unseen In this work, Remote Sensing (RS) multispectral images with trained QA discussed....
Treatment of patients undergoing prolonged weaning from mechanical ventilation includes repeated spontaneous breathing trials (SBTs) without respiratory support, whose duration must be balanced critically to prevent over- and underload musculature. This study aimed develop a machine learning model predict the unassisted breathing. Structured clinical data specialized unit were used (1) classifier qualitatively an increase duration, (2) regressor quantitatively precise SBTs on next day, (3)...
High-Performance Computing (HPC) has recently been attracting more attention in remote sensing applications due to the challenges posed by increased amount of open data that are produced daily Earth Observation (EO) programs. The unique parallel computing environments and programming techniques integrated HPC systems able solve large-scale problems such as training classification algorithms with large amounts Remote Sensing (RS) data. This paper shows state-of-the-art deep Convolutional...
Recent developments in Quantum Computing (QC) have paved the way for an enhancement of computing capabilities. Machine Learning (QML) aims at developing (ML) models specifically designed quantum computers. The availability first processors enabled further research, particular exploration possible practical applications QML algorithms. In this work, formulations Support Vector (SVM) are presented. Then, their implementation using existing technologies is discussed and Remote Sensing (RS)...
Turbulent flow is a complex and vital phenomenon in fluid dynamics, as it the most common type of both natural artificial systems. Traditional methods studying turbulent flow, such computational dynamics experiments, have limitations high costs, experiment restricted problem scales sizes. Recently, intelligence has provided new avenue for examining which can help improve our understanding its features physics various applications. Strained occurs presence gravity situations combustion...
Abstract In this work, we couple the functional-structural plant model CPlantBox to Unreal Engine by exploiting implemented raytracing pipeline evaluate light influx on surface. There are many approaches for photosynthesis computation and evaluation, though they typically limited versatility, compute speed, or operate much coarser resolutions. This work specifically addresses concern that data generation pipelines tend be unresponsive do not include model-based knowledge as part of pipeline....
The dynamics of inertial particles in turbulent flow are complex, and practice, gravity influences particle dynamics. However, the effects have not been appropriately investigated using numerical approaches. This study provides first empirical evidence a data-driven deep learning (DL) model to predict velocity, displacement, acceleration strained particle-laden flow. introduces DL experimental data from Hassanian et al., who distorted within specific range Taylor microscale Reynolds number,...
Abstract This study proposes and evaluates a hybrid gated recurrent unit--long short-term memory (GRU--LSTM) deep learning (DL) model to forecast ambient temperature, key factor influencing photovoltaic (PV) module temperature efficiency. Ambient varies due range of environmental weather conditions is not consistently predictable during daytime. However, it often assumed remain constant in PV design solar power production calculations. To address unsolved issue, the exploits DL by...
Many production Grid and e-Science infrastructures have begun to offer services end-users during the past several years with an increasing number of scientific applications that require access a wide variety resources in multiple Grids. Therefore, Interoperation Now—Community Group Open Forum—organizes manages interoperation efforts among those reach goal world-wide vision on technical level near future. This contribution highlights fundamental approaches group discusses open standards...
Advances in remote sensing hardware have led to a significantly increased capability for high-quality data acquisition, which allows the collection of remotely sensed images with very high spatial, spectral, and radiometric resolution. This trend calls development new techniques enhance way that such unprecedented volumes are stored, processed, analyzed. An important approach deal massive information is compression, related how compressed before their storage or transmission. For instance,...
This paper presents Sen4Map, a large-scale benchmark dataset designed to enhance the capability of generating land-cover maps using Sentinel-2 data. Comprising non-overlapping <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$64\times 64$</tex-math></inline-formula> patches extracted from time series images, spans 335,125 geo-tagged locations across European Union. These are associated with detailed and...