Refine
Year of publication
- 2021 (392) (remove)
Document type
- Article (peer-reviewed) (159)
- Conference Proceeding (83)
- Part of a Book (51)
- Contribution to a Periodical (45)
- Other (33)
- Book (15)
- Doctoral Thesis (4)
- Report (1)
- Working Paper (1)
Language
- English (240)
- German (151)
- Multiple languages (1)
Is part of the Bibliography
- Yes (392) (remove)
Keywords
- Online-Ressource (13)
- Electrical impedance tomography (12)
- Corona (8)
- E-Learning (7)
- Machine learning (6)
- Mechanical ventilation (5)
- Virtual patient (5)
- Detraining (4)
- Lean body mass (4)
- Acute respiratory failure (3)
- Autism spectrum disorder (ASD) (3)
- Bone mineral density (3)
- Critical care (3)
- Cytotoxicity (3)
- Digital twin (3)
- Electrical impedance tomography (EIT) (3)
- Facial emotion recognition (FER) (3)
- Grinding (3)
- IoT (3)
- Lung mechanics (3)
- Micro-grinding (3)
- Microwave imaging (3)
- Oulu-CASIA (3)
- Podcast (3)
- Respiration (3)
- Simulation (3)
- Umfrage (3)
- Vortrag (3)
- ARDS (2)
- Acute respiratory distress syndrome (2)
- Adaptive optics (2)
- Additive manufacturing (2)
- Basis function (2)
- Betulinic acid (2)
- Big data (2)
- Biomechanics (2)
- Blockchain (2)
- Bone screw (2)
- CNN (2)
- CNN generalisability (2)
- COVID-19 pneumonia (2)
- Chatbot (2)
- Classification (2)
- Context-aware systems (2)
- Convolutional neural network (2)
- Deep learning (2)
- Digital transformation (2)
- Digital twins (2)
- Exercise (2)
- Fluorescence lifetime (2)
- Fluorescence lifetime imaging microscopy (FLIM) (2)
- Harmonic analysis (2)
- Hygiene (2)
- LSTM (2)
- Laparoscopic images (2)
- Laparoscopy (2)
- Lysosomotropism (2)
- MRSA (2)
- Manufacturing (2)
- Men (2)
- Metabolic syndrome (2)
- Microplastic (2)
- Modeling (2)
- Modelling (2)
- Muscle strength (2)
- Nanoparticles (2)
- Oleanolic acid (2)
- PEEP (2)
- PEEP titration (2)
- Polymers (2)
- Reference model (2)
- Resistance exercise (2)
- Resource discovery (2)
- Sarcopenia (2)
- Security (2)
- Smart screwdriver (2)
- Software engineering (2)
- Surface roughness (2)
- Surgical actions (2)
- Surgical tool detection (2)
- SusAF (2)
- Sustainability (2)
- Synthesis (2)
- Tidal volume (2)
- Titanium (2)
- Torque limitation (2)
- Virtual reality (2)
- Whole-body electromyostimulation (2)
- mHealth (2)
- 1,2,4-triazolo[4,3-a]pyridine (1)
- 1,4-cyclohexyldiamines (1)
- 2D differential microcoils (1)
- 3D-Data (1)
- 5G (1)
- AI in manufacturing (1)
- Abdominal breathing (1)
- Acceptance (1)
- Accuracy in volume delivery (1)
- Active focusing (1)
- Acute myeloid leukaemia (1)
- Acute pulmonary embolism (1)
- Acute respiratory distress syndrome (ARDS) (1)
- Additive Fertigung (1)
- Adversarial attack (1)
- Adversarial image (1)
- Aerobic capacity (1)
- Aging (1)
- Airway obstruction (1)
- AlexNet (1)
- Alkaloids (1)
- Amorfrutin A (1)
- Amorfrutin B (1)
- Angiogenesis (1)
- Anomalous co-deposition (1)
- Anti-gravity straining maneuver (1)
- Antibacterial (1)
- Antibiofilm (1)
- Antimicrobial materials (1)
- Antimicrobial peptide (1)
- Antimicrobial susceptibility testing (1)
- Appropriate resolution prototyping (1)
- Arteries (1)
- Artery (1)
- Artificial intelligence (1)
- Artificial neural network (1)
- Assessment (1)
- Asynchrony (1)
- Atomic layer deposition (ALD) (1)
- Audit (1)
- Autofluorescence (1)
- Azelastine (1)
- Bacteria (1)
- Bacterial infections (1)
- Bacteriocin (1)
- Bacteriophages (1)
- Barkhausen noise (1)
- Base model (1)
- Bath hydrodynamics (1)
- Bedside monitoring (1)
- Benzylamides (1)
- Bewegungsförderung (1)
- Bewertungsverfahren (1)
- Biocatalysis (1)
- Biomedical control (1)
- Biomedical imaging systems (1)
- Blutspende (1)
- Body cameras (1)
- Body composition (1)
- Body fat (1)
- Body fat mass (1)
- Body position change (1)
- Bone Mineral Density (1)
- Bone screws (1)
- Bone tissue engineering (1)
- Boundary detection (1)
- Breathing (1)
- Breathing model (1)
- CAR T cells (1)
- CD133 (1)
- CD73 (1)
- COVID-19 disease characteristics (1)
- COVID-19 pandemic (1)
- COVID‐19 (1)
- COVID‑19 (1)
- CPET (1)
- CSI (1)
- CSI-GE (1)
- CT segmentation (1)
- Cancer (1)
- Cancer immunotherapy (1)
- Carbohydrates (1)
- Carbon fiber-reinforced polyether ether ketone (1)
- Case management (1)
- Central sensitivity syndromes (1)
- Central sensitization (1)
- Central sensitization inventory (1)
- Ceramics grinding (1)
- Chemieprozesse Werkstoffe (1)
- Chest breathing (1)
- Chip formation energy (1)
- Clinical simulation in nursing (1)
- Clinical variables (1)
- Cloud (1)
- Cloud computing (1)
- Cloud-edge computing (1)
- Clustering (1)
- Combination therapy (1)
- Compliance (1)
- Concept drift detection (1)
- Configural frequency analysis (1)
- Confocal microscopy (1)
- Context-aware system (1)
- Contingency (1)
- Control (1)
- Control of voluntary movements (1)
- Conventions (1)
- Convolutional neural networks (1)
- Cooperative actuators (1)
- Coronary microvasculature (1)
- Coronavirus disease 2019 (1)
- Correlation (1)
- Cost based metric (1)
- Cotton (1)
- Covid-19 (1)
- Critical large bone defects (1)
- Cross company business model (1)
- Crystal structure (1)
- Cutting force (1)
- Cutting forces (1)
- Cycling (1)
- Cylindrical grinding process Grinding burn (1)
- Cytokine storm (1)
- DHT (1)
- Data Science (1)
- Data-driven (1)
- Data-driven decisions (1)
- Datenanalyse (1)
- Decision support systems for the control of physiological (1)
- Dementia (1)
- Dextran Hydrogel (1)
- Dextran hydrogel (1)
- Diabetes (1)
- Diamond grinding wheel (1)
- Diffusion layer thickness (1)
- Digital health intervention (1)
- Digital human modeling (DHM) (1)
- Digital self-tracking (1)
- Digital signal processing (1)
- Digital technologies (1)
- Digitale Souveränität (1)
- Digitale Transformation (1)
- Digitalization (1)
- Digizitation (1)
- Dimensional layout conception (1)
- Distributed DNN (1)
- Distributed data validation network (1)
- Distributed ledger (1)
- Domain expert interviews (1)
- Double Homeobox 4 (DUX4) (1)
- Downstream signalling (1)
- Dressing (1)
- Duplex lateral flow assay (1)
- Eactive oxygen species (1)
- Early mobilizations (1)
- Early postmenopause (1)
- Ectopic fat (1)
- Eddy-current (1)
- Eddy-current transducers (1)
- Edge Computing (1)
- Edge cloud computing (1)
- Edge security (1)
- Education technology (1)
- Educational objectives (1)
- Elastance (1)
- Electrical bioimpedance (1)
- Electrical impedance system (1)
- Electrical impedance tomograph (1)
- Electrochemical deposition (1)
- Electromagnetic simulation (1)
- Electrostatic actuation (1)
- Electrostatic actuator (1)
- Elongation of very long-chain fatty acids (1)
- Emergency machine guarding (1)
- Endocrine disrupting chemicals (1)
- Endocrine-disrupting compounds (1)
- Endoscopic video (1)
- Energy forecast (1)
- Entwicklungsprozess (1)
- Enzymatic hydrolysis (1)
- Enzymatic resolution (1)
- Epigenetic (1)
- Error prediction (1)
- Ersatzteillogistik (1)
- Ethanol (1)
- Euro area (1)
- Exercise physiology (1)
- Exercise training (1)
- Expert system (1)
- Explainable ML (1)
- Extended reality (1)
- Eye (1)
- Eye-tracking (1)
- FEM (1)
- Facioscapulohumeral muscular dystrophy (FSHD) (1)
- Factory operations commission (1)
- Fat mass (1)
- Fatty acid oxidation (1)
- Fatty muscle infiltration (1)
- Feature extraction (FE) (1)
- Fed-batch strategy (1)
- Fermentation (1)
- Fernsehbeitrag (1)
- Filter design (1)
- Filter implementation (1)
- Filter-based feature selection methods (1)
- Finite difference time domain (1)
- Finite difference time domain (FDTD) (1)
- Finite impulse response filter (1)
- Fluorinated monosaccharides (1)
- Food (1)
- Fuel injection nozzle (1)
- Fuzzy logic (1)
- Galactosidase (1)
- Glas Herstellung (1)
- Global inhomogeneity index (1)
- Global ventilation (1)
- Glucose (1)
- Glucosidase (1)
- Glycosides (1)
- Grafts (1)
- Grinding burn (1)
- Grinding specific energy (1)
- Grinding wheel conditioning (1)
- Grinding wheel profiling (1)
- H-bonding (1)
- HMM (1)
- Haemodynamics (1)
- Hardness measurement (1)
- Health care (1)
- Hearing impairment (1)
- Heart transplantation (1)
- Hematopoietic stem and progenitor cells (1)
- Hidden Markov model (1)
- Hierarchical microstructures (1)
- High flow nasal cannula (1)
- High-intensity exercise (1)
- High-throughput 3D tumor-stroma model (1)
- Household wealth (1)
- Human-machine interaction (1)
- Human-robot collaboration (1)
- Hybrid AI (1)
- Hybrids (1)
- Hypoxia (1)
- Hysteresis loop analysis (1)
- Hysteresis loop model (1)
- Hysteresis model (1)
- Hysteretic lung mechanics (1)
- ICU (1)
- IMAT (1)
- Identification (1)
- Illumina MiSeq ® (1)
- Image processing (1)
- Image segmentation (1)
- Immunoassay (1)
- Immunology (1)
- Impedance measurement (1)
- Implants (1)
- Implementierung (1)
- In-vivo (1)
- Inchworm motor (1)
- Individual support on reintegration (1)
- Inductively coupled plasma mass spectrometry (ICP-MS) (1)
- Industry 4.0 (1)
- Inertial sensing (1)
- Infectious disease (1)
- Inflammatory Cells (1)
- Inhibitor (1)
- Inline measurement method (1)
- Innovationsmanagement (1)
- Insertion speed (1)
- Insurance (1)
- Intensive care (1)
- Intermittent hypoxia (1)
- Intermuscular adipose tissue (1)
- Intervention design (1)
- Intra-abdominal pressure (1)
- Iridium oxide (1)
- Key frame selection (1)
- Keynote (1)
- Krankenversicherungen (1)
- Kunststoff Herstellung (1)
- Labor force participation (1)
- Laparoscopic procedure (1)
- Laparoscopic video (1)
- Laser ablation (1)
- Laser power intensity (1)
- Lateral flow assays (LFA) (1)
- Laundry hygiene (1)
- Leakage correction (1)
- Lebenswissenschaften (1)
- Leg strength (1)
- Legacy machines (1)
- Life prediction (1)
- Limb occlusion (1)
- Linearity (1)
- Listeria monocytogenes (1)
- Locality aware (1)
- Loess smoothing (1)
- Low back pain (1)
- Low power (1)
- Lung cancer (1)
- Lung compliance (1)
- Lung imaging (1)
- Lung lesion (1)
- Lung perfusion (1)
- Lung perfusion and ventilation (1)
- Lung recruitability (1)
- Lung ventilation (1)
- Lung ventilation monitoring (1)
- Lung-protective ventilation (1)
- MALDI biotyping (1)
- MEMS (1)
- MLOps Mlflow DVC (1)
- MOEMS (1)
- Machine perfusion (1)
- Machine/ DeepLearning (1)
- Magnetostrictive (1)
- Maintenance (1)
- Maladaptive Überzeugungen (1)
- Maltose (1)
- Marathon training (1)
- Material removal mechanism (1)
- Material removal rate (1)
- Mathematical model (1)
- Mechanical power (1)
- Medical instrumentation (1)
- Menopausal transition (1)
- Mesenchymal stem cells (1)
- MetS Z-Score (1)
- Metabolites (1)
- Metatranscriptome (1)
- Metrics (1)
- Micro non-destructive evaluation (1)
- Micro volume (1)
- Micro-optical electro-mechanical system (MOEMS) (1)
- Microbiota (16S) (1)
- Microfabricated microcoils (1)
- Microvascular dysfunction (1)
- Miniaturization (1)
- Minimum viable product (1)
- Mobile-access edge computing (1)
- Mobility management (1)
- Model-assisted design of experiments (1)
- Molecular biology (1)
- Monetary policy (1)
- Monitoring (1)
- Monte Carlo methods (1)
- Mortality (1)
- Motion capture system (1)
- Multidrug resistance (1)
- Multiphoton ionisation (1)
- Multipurpose exercise (1)
- Muscle mass (1)
- Muscle quality (1)
- Muscle tissue (1)
- Myocardial microcirculation (1)
- N-Oxides (1)
- NCS (1)
- NMR spectroscopy (1)
- Nanoantibiotics (1)
- Nanocrystalline nickel-cobalt alloys (1)
- Natural language processing (1)
- Network prediction visualization (1)
- Neural network (1)
- Neural networks (1)
- Neuro-fuzzy (1)
- Non-destructive test method (1)
- Non-destructive testing (1)
- Noninvasive monitoring (1)
- Nonlinearity (1)
- Nurse education (1)
- OR-layout (1)
- Obesity (1)
- Obstructive lung disease (1)
- Occupational fields (1)
- Older men (1)
- Older workers (1)
- Online-Kommentar (1)
- Open-source (1)
- Operating room (OR) (1)
- Optical simulation (1)
- Organ function (1)
- Orthopaedic surgery (1)
- Osseointegration (1)
- Osteoporosis (1)
- Outcome prediction (1)
- Overdistension (1)
- PD-1 (1)
- PE-ALD (1)
- Particle image velocimetry (1)
- Pathogen identification (1)
- Patient-centered outcome (1)
- Pay-as-you-live (1)
- Peer-reviewed conference (1)
- Performance (1)
- Perfusion (1)
- Perfusion separation (1)
- Personalizing ventilation strategies (1)
- Pflege (1)
- Phasor analysis (1)
- Phenotype (1)
- Phthalates (1)
- Physical optics (1)
- Physiological modeling (1)
- Pilocarpine (1)
- Plasma enhanced atomic layer deposition (PEALD) (1)
- Platanic acid (1)
- Plowing (1)
- Point-of-Care diagnostics (1)
- Point-of-care (POC) diagnostics (1)
- Polyester (1)
- Polyether Ether Ketone composite (1)
- Polyether ether ketone (PEEK) (1)
- Polyetheretherketone (PEEK) (1)
- Portfolio efficiency (1)
- Poster (1)
- Posture (1)
- Pragmatism (1)
- Prediction (1)
- Preprint (1)
- Presence (1)
- Prevention (1)
- Primärprävention (1)
- Prior information (1)
- Process efficiency (1)
- Product engineering (1)
- Production (1)
- Production data (1)
- Produktentwicklung (1)
- Prognosis (1)
- Progressive information (1)
- Prone position ventilation (1)
- Proteolysis (1)
- Prozesse Chemie Werkstoffe (1)
- Pruritic papules (1)
- Pruritus (1)
- Pulmonary function testing (1)
- Pulmonary lesion (1)
- Python (1)
- Quality assurance (1)
- Quality by design (1)
- Quantifying value of data (1)
- Quantitative analysis (1)
- Quantum dots image processing (1)
- RNA sequencing (1)
- ROS quenching (1)
- Real returns (1)
- Real time (1)
- Real time computing (1)
- Recirculation (1)
- Redistribution index (1)
- Region of interest (1)
- Regional lung ventilation (1)
- Regional ventilation (1)
- Regional ventilation distribution (1)
- Reminisence therapy (1)
- Resistance profiling (1)
- Resistance training (1)
- Respiratory mechanics (1)
- Return to work (1)
- Rhodamine B (1)
- Risk analysis (1)
- Robotics (1)
- Role understanding (1)
- SARS-CoV-2 (1)
- SCLC (1)
- SHAP values (1)
- SOI (1)
- SRB assay (1)
- Scoring system (1)
- Segmentation (1)
- Sekundärprävention (1)
- Selbstvermessung (1)
- Semantic augmentation (1)
- Semantic segmentation (1)
- Sensor fusion (1)
- Sensor location (1)
- Sepsis (1)
- Serology (1)
- Service Management (1)
- Service design (1)
- Service innovation (1)
- Service prototyping (1)
- Service quality (1)
- Shop floor (1)
- Silicon nitride (1)
- Silicon-on-insulator (SOI) (1)
- Silicone phantom (1)
- Simulation design (1)
- Single grit scratch test (1)
- Single-pass honing tool (1)
- Small data (1)
- Smart-shirt (1)
- Smartphone-based system (1)
- Software development practitioners (1)
- Software product (1)
- Software sustainability (1)
- Softwareentwicklung (1)
- Solitary pulmonary nodule (1)
- Sorption (1)
- Sozio-technische Systeme (1)
- Spatial-temporal information (1)
- Specific energy (1)
- Specific grinding energy (1)
- Sphingolipid metabolism (1)
- Stability of pressurization (1)
- Standard EIT parameters (1)
- Standardized 3D Model (1)
- Starch hydrolysis (1)
- Static cutting density (1)
- Stem cell therapy (1)
- Strength and power (1)
- Strictures (1)
- Subacromial pain syndrome (1)
- Subject orientation (1)
- Superhydrophobic properties (1)
- Supervised learning (1)
- Surface topography (1)
- Surgical phase recognition (1)
- Surgical tool presence detection (1)
- Sustainability design (1)
- Sustainability effects (1)
- Tageszeitung (1)
- Task migration (1)
- Technology services (1)
- Test rig (1)
- Thin film coating (1)
- Tidal volumes (1)
- Time series (1)
- Tissue -mimicking phantom (1)
- Titanium dioxide (1)
- Titrate of positive end‑ expiratory pressure (1)
- Tool contour evolution (1)
- Tool stiffness (1)
- Torque measurement (1)
- Torque sensor (1)
- Trace elements (1)
- Training response (1)
- Treatment strategies (1)
- Trunk strength (1)
- Tubular structures (1)
- Tumor Stroma Interaction (1)
- Tumor–stroma interaction (1)
- Tutor (1)
- Ultra-wideband (1)
- Ultra-wideband (UWB) (1)
- Ultrashort pulse laser (1)
- Ultrashort-pulsed laser (1)
- Undeformed chip thickness (1)
- Urethra (1)
- Ursolic acid (1)
- Usability Praktiker (1)
- User eXperience (1)
- User experience (1)
- User requirements engineering (1)
- V/Q (1)
- Validation (1)
- Validity (1)
- Vascular sprouting (1)
- Venipuncture (1)
- Ventilation distribution (1)
- Ventilation heterogeneity (1)
- Ventilator efficiency (1)
- Ventilator performance (1)
- Verfügbarkeitsoptimierung (1)
- Video-assisted thoracoscopic surgery (VATS) (1)
- Viral genetics (1)
- Viral infection (1)
- Virtual image data (1)
- Visual attention network (1)
- WB-EMS (1)
- Washing machine (1)
- Wearables (1)
- Werkstoffe Chemie (1)
- Wheel loading (1)
- Wire electrical discharge machining (1)
- Wireless transmission (1)
- eHealth (1)
- Übungstherapie (1)
Chemie der Werkstoffe
(2021)
The Elephant in the Room - Educating Practitioners on Software Development for Sustainability
(2021)
Umsetzung eines Pay-as-you-Live Systems : Konzeptioneller Ansatz für ein eigenständiges PAYL-System
(2021)
Abrasive tools
(2021)
Abrasives
(2021)
In dem vorliegenden Beitrag wird der aktuelle Trend, Payas-you-live-Systeme (PAYL) in Verbindung mit Krankenversicherungen anzubieten, analysiert. PAYL-Systeme bedeutet konkret die kontinuierliche Erfassung von Gesundheitsdaten mithilfe technischer Geräte und Übermittlung dieser Daten an Versicherungen sowie die Auszahlung von Boni für erreichte Fitnessziele. Zunächst wird eine Definition von PAYL-Systemen dargelegt, dann werden die technischen Rahmenbedingungen erläutert, schließlich werden die Auswirkungen dieser soziotechnischen Systeme näher beleuchtet. Dies geschieht auf Grundlage unserer empirischen Untersuchung. Die drei identifizierten Hauptkonflikte betreffen die Genese von PAYL, seine Auswirkungen auf den Wert der Datensouveränität besonders für Versicherte und die Schwierigkeit, für den Anspruch auf Prävention und Kostenersparnis durch PAYL Evidenz zu erzeugen. Diese Konflikte werden diskutiert, um sowohl die direkten wie auch indirekten Auswirkungen der Digitalisierung und der Ökonomisierung des Sozialen durch PAYL zu beleuchten.
Nowadays, machine learning projects have become more and more relevant to various real-world use cases. The success of complex Neural Network models depends upon many factors, as the requirement for structured and machine learning-centric project development management arises. Due to the multitude of tools available for different operational phases, responsibilities and requirements become more and more unclear. In this work, Machine Learning Operations (MLOps) technologies and tools for every part of the overall project pipeline, as well as involved roles, are examined and clearly defined. With the focus on the inter-connectivity of specific tools and comparison by well-selected requirements of MLOps, model performance, input data, and system quality metrics are briefly discussed. By identifying aspects of machine learning, which can be reused from project to project, open-source tools which help in specific parts of the pipeline, and possible combinations, an overview of support in MLOps is given. Deep learning has revolutionized the field of Image processing, and building an automated machine learning workflow for object detection is of great interest for many organizations. For this, a simple MLOps workflow for object detection with images is portrayed.
While the number of devices connected together as the Internet of Things (IoT) is growing, the demand for an efficient and secure model of resource discovery in IoT is increasing. An efficient resource discovery model distributes the registration and discovery workload among many nodes and allow the resources to be discovered based on their attributes. In most cases this discovery ability should be restricted to a number of clients based on their attributes, otherwise, any client in the system can discover any registered resource. In a binary discovery policy, any client with the shared secret key can discover and decrypt the address data of a registered resource regardless of the attributes of the client. In this paper we propose Attred, a decentralized resource discovery model using the Region-based Distributed Hash Table (RDHT) that allows secure and location-aware discovery of the resources in IoT network. Using Attribute Based Encryption (ABE) and based on predefined discovery policies by the resources, Attred allows clients only by their inherent attributes, to discover the resources in the network. Attred distributes the workload of key generations and resource registration and reduces the risk of central authority management. In addition, some of the heavy computations in our proposed model can be securely distributed using secret sharing that allows a more efficient resource registration, without affecting the required security properties. The performance analysis results showed that the distributed computation can significantly reduce the computation cost while maintaining the functionality. The performance and security analysis results also showed that our model can efficiently provide the required security properties of discovery correctness, soundness, resource privacy and client privacy.
Additives and polymer composition influence the interaction of microplastics with xenobiotics
(2021)
In Industry 4.0 machine learning approaches are a state-of-the art for predictive maintenance, machine condition monitoring, and others. Distributed decision trees are one of the learning algorithms for such applications. A new approach of node based parallelization for the construction is presented and allows to classify data through a network of nodes. Attacks on the nodes are discussed based on different attack scenarios and attack classifications are presented. A thorough analysis of protection measurements is given, such that classification is not maliciously modified by an attacker. Different countermeasures are proposed and analyzed. A quorum-based system allows for a good balance between computational overhead and robustness of the algorithm.
Durch die zunehmende Intelligenz der Produkte und die Möglichkeiten der Vernetzung zu einem Internet-der-Dinge entstehen zusätzliche Potenziale durch die Verarbeitung von Daten und das Angebot von datenbasierten, smarten Services. In diesem Artikel wird ein Rahmen für die Gestaltung der Digitalen Transformation für Dienstleistungen anhand des Remote Services Continuums aufgezeigt, die digitale Wertschöpfungskette beschrieben und eine Roadmap zur Erschließung dieser Potenziale dargestellt.
Biosynthesis of iron oxide magnetic nanoparticles using clinically isolated Pseudomonas aeruginosa
(2021)
Distributed machine learning algorithms that employ Deep Neural Networks (DNNs) are widely used in Industry 4.0 applications, such as smart manufacturing. The layers of a DNN can be mapped onto different nodes located in the cloud, edge and shop floor for preserving privacy. The quality of the data that is fed into and processed through the DNN is of utmost importance for critical tasks, such as inspection and quality control. Distributed Data Validation Networks (DDVNs) are used to validate the quality of the data. However, they are prone to single points of failure when an attack occurs. This paper proposes QUDOS, an approach that enhances the security of a distributed DNN that is supported by DDVNs using quorums. The proposed approach allows individual nodes that are corrupted due to an attack to be detected or excluded when the DNN produces an output. Metrics such as corruption factor and success probability of an attack are considered for evaluating the security aspects of DNNs. A simulation study demonstrates that if the number of corrupted nodes is less than a given threshold for decision-making in a quorum, the QUDOS approach always prevents attacks. Furthermore, the study shows that increasing the size of the quorum has a better impact on security than increasing the number of layers. One merit of QUDOS is that it enhances the security of DNNs without requiring any modifications to the algorithm and can therefore be applied to other classes of problems.
Training of neural networks requires often high computational power and large memory on Graphics Processing Unit (GPU) hardware. Many cloud providers such as Amazon, Azure, Google, Siemens, etc, provide such infrastructure. However, should one choose a cloud infrastructure or an on premise system for a neural network application, how can these systems be compared with one another? This paper investigates seven prominent Machine Learning benchmarks, which are MLPerf, DAWNBench, DeepBench, DLBS, TBD, AIBench, and ADABench. The recent popularity and widespread use of Deep Learning in various applications have created a need for benchmarking in this field. This paper shows that these application domains need slightly different resources and argue that there is no standard benchmark suite available that addresses these different application needs. We compare these benchmarks and summarize benchmarkrelated datasets, domains, and metrics. Finally, a concept of an ideal benchmark is sketched.
Potentials of Semantic Image Segmentation Using Visual Attention Networks for People with Dementia
(2021)
Due to the increasing number of dementia patients, it is time to include the care sector in digitization as well. Digital media, for example, can be used on tablets in memory care and have considerable potential for reminiscence therapy for people with dementia. The time consuming assembly of digital media content has to be automated for the caretakers.
This work analyzes the potentials of semantic image segmentation with Visual Attention Networks for reminiscence therapy sessions. These approaches enable the selection of digital images to satisfy the patients individual experience and biographically. A detailed comparison of various Visual Attention Networks evaluated by the BLEU score is shown. The most promising networks for semantic image segmentation are VGG16 and VGG19.
In edge/fog computing infrastructures, the resources and services are offloaded to the edge and computations are distributed among different nodes instead of transmitting them to a centralized entity. Distributed Hash Table (DHT) systems provide a solution to organizing and distributing the computations and storage without involving a trusted third party. However, the physical locations of nodes are not considered during the creation of the overlay which causes some efficiency issues. In this paper, Locality aware Distributed Addressing (LADA) model is proposed that can be adopted in distributed infrastructures to create an overlay that considers the physical locations of participating nodes. LADA aims to address the efficiency issues during the store and lookup processes in DHT overlay. Additionally, it addresses the privacy issue in similar proposals and removes any possible set of fixed entities. Our studies showed that the proposed model is efficient, robust and is able to protect the privacy of the locations of the participating nodes.