Filtern
Erscheinungsjahr
Dokumenttyp
Volltext vorhanden
- ja (44)
Gehört zur Bibliographie
- nein (44)
Schlagworte
- Elektrofahrzeug (5)
- Biodiversität (4)
- CO2-Bilanz (4)
- Elektromobilität (4)
- Fermentation (4)
- Maschinelles Lernen (4)
- Biomonitoring (3)
- Insekten (3)
- Klimaänderung (3)
- Rapid Prototyping <Fertigung> (3)
- additive manufacturing (3)
- 3D printing (2)
- 3D-Druck (2)
- Alkoholmissbrauch (2)
- Anomalie <Medizin> (2)
- Anomalieerkennung (2)
- Bioreaktor (2)
- CO2 (2)
- Convolutional Neural Network (2)
- Deutschland (2)
- Intervention <Medizin> (2)
- Jugend (2)
- Künstliche Intelligenz (2)
- LCA (2)
- LTER (2)
- Magnetisches Trennverfahren (2)
- Personenkraftwagen (2)
- Umweltbilanz (2)
- Universität (2)
- alcohol (2)
- anomaly detection (2)
- biodiversity (2)
- carbon footprint (2)
- carbon footprinting (2)
- climate policy (2)
- efficiency trade-offs (2)
- electric cars (2)
- fermentation (2)
- global warming potential (2)
- greenhouse gas emissions (2)
- high-gradient magnetic separation (2)
- insect monitoring (2)
- internet (2)
- life cycle assessment (2)
- mRNA-Impfstoff (2)
- machine learning (2)
- magnetic beads (2)
- modeling (2)
- optimization (2)
- renewable energy (2)
- university carbon footprint (2)
- university sustainability (2)
- young people (2)
- zero emission university (2)
- ALAN (1)
- ATR-Technik (1)
- Agent <Künstliche Intelligenz> (1)
- Agglomerieren (1)
- Algorithmus (1)
- Apoptosis (1)
- App <Programm> (1)
- Art (1)
- BASF Ultrafuse (1)
- BEV (1)
- BEV (battery electric vehicle) (1)
- BPA (1)
- Bartak (1)
- Batterie (1)
- Batteriefahrzeug (1)
- Bestäuber (1)
- Bewertung (1)
- Bild (1)
- Bilderkennung (1)
- Bildung für nachhaltige Entwicklung (1)
- Bildverarbeitung (1)
- Biofilm (1)
- Bioklima (1)
- Biomasse (1)
- Bioverfahrenstechnik (1)
- Bisphenol A (1)
- Boden (1)
- Bodenorganismus (1)
- Bodentemperatur (1)
- Branch-and-Bound-Methode (1)
- CNN (1)
- CO2 emissions (1)
- Charpy impact energy (1)
- China (1)
- Computerfigur (1)
- Cyanobakterien (1)
- DNN (1)
- Deep learning (1)
- Demontage (1)
- Dieselkraftstoff (1)
- Diskriminanzanalyse (1)
- Diuron (1)
- E-Learning (1)
- E. coli (1)
- EBV (1)
- EHR (1)
- ESD (1)
- Elektronische Patientenakte (1)
- Emissionsverringerung (1)
- Energie (1)
- Energiemodell (1)
- Environmental Campus Birkenfeld (1)
- Escherichia coli (1)
- Europa (1)
- Europe (1)
- European diesel car boom (1)
- European perch (1)
- FT-IR-Spektroskopie (1)
- Falle (1)
- Fed-batch-Verfahren (1)
- Festigkeit (1)
- Flussbarsch (1)
- Forschung (1)
- Frequenzumsetzung (1)
- Frequenzverdopplung (1)
- Fused Deposition Modeling (1)
- Fuzzy-Logik (1)
- GA-ANFIS (1)
- GA-FUZZY (1)
- GA-GA-FUZZY (1)
- GHG (1)
- GHG accounting and reporting (1)
- GWP (1)
- Genetischer Algorithmus (1)
- Gesundheitsökonomie (1)
- Handy (1)
- Herzmuskelkrankheit (1)
- Hydrothermale Karbonisierung (1)
- Höheres Bildungswesen (1)
- ICU (1)
- Industrieroboter (1)
- Integriertes Lernen (1)
- Intensivpflege (1)
- Intensivstation (1)
- Internet (1)
- K2Al2B2O7 (1)
- KABO (1)
- Klassifikation (1)
- Klimaschutz (1)
- Kohlendioxidemission (1)
- Konturfindung (1)
- Kraftfahrzeugindustrie (1)
- Kraftwagen (1)
- Kristall (1)
- Kunststoff (1)
- Künstliche Beatmung (1)
- Laborparameter (1)
- Lasertechnologie (1)
- Leistung (1)
- Lernsoftware (1)
- Lichtverschmutzung (1)
- Lufttemperatur (1)
- Malaise trap (1)
- Markforged (1)
- Materialermüdung (1)
- Medizinische Informatik (1)
- Messung (1)
- Metaanalyse (1)
- Meteorologische Station (1)
- Methanol-Analytik (1)
- Methode der kleinsten Quadrate (1)
- Methylotrophe Organismen (1)
- Mikroklima (1)
- Modell (1)
- NLO crystals (1)
- NLO-Kristall (1)
- Nachhaltigkeit (1)
- Nahrungskette (1)
- Nanyang Technological University (1)
- Naturschutz (1)
- Neuro-Fuzzy-System (1)
- Neuronales Netz (1)
- Nichtlineare Diffusion (1)
- Nichtlineare Optik (1)
- Nullemission (1)
- PETG (1)
- Parasit (1)
- Pellet (1)
- Penicillium (1)
- Penicillium sp. (1)
- Perca fluviatilis (1)
- Petri nets (1)
- Pflanzenkohle (1)
- Photoreaktor (1)
- Physik (1)
- Physikunterricht (1)
- Pichia pastoris (1)
- Plug-in-Hybrid (1)
- Proteaseinhibitor (1)
- Prozessanalytik (1)
- Prozessmanagement (1)
- Prozessmesstechnik (1)
- Raucherentwöhnung (1)
- Recycling (1)
- Rekursives neuronales Netz (1)
- Robotertechnik (1)
- Rotationsdispersion (1)
- Ruß (1)
- Selbstorganisierende Karte (1)
- Selektives Laserschmelzen (1)
- Sepsis (1)
- Singapur (1)
- Soziale Norm (1)
- Sporenbildung (1)
- Statistik (1)
- Student (1)
- Studiengang (1)
- Suchverfahren (1)
- Süßwasser (1)
- Teer (1)
- Townes (1)
- Umwelt-Campus Birkenfeld (1)
- Umweltdaten (1)
- Unterstützungssystem <Informatik> (1)
- VentAI (1)
- Vergleich (1)
- Verteilung (1)
- Virtuelles Laboratorium (1)
- Wassertiere (1)
- Wellenlänge (1)
- Windturbine (1)
- YAB (1)
- YAl3(BO3)4 (1)
- Zigarettenrauch (1)
- Zulaufsatzkultur-Fermentationen (1)
- active learning (1)
- adaptive neuro fuzzy system (1)
- adsorption mechanism (1)
- agglomeration (1)
- alternating least squares (1)
- apoptosis (1)
- aquatic subsidies (1)
- artificial intelligence (1)
- bachelor degree programs in business administration and mechanical engineering (1)
- battery (1)
- battery electric vehicle (1)
- battery electric vehicles (1)
- battery production (1)
- battery second use (1)
- battery size (1)
- biocarriers (1)
- bioclimatic variables (1)
- biofilm (1)
- bioprocess engineering (1)
- bioreactor internals (1)
- black carbon (1)
- blended learning (1)
- branch and bound search algorithm (1)
- break-even mileages (1)
- break-even production (1)
- building emissions (1)
- carbon mass balance constraint (1)
- carbon offsetting (1)
- classification (1)
- climate change (1)
- climate change impact (1)
- climate change mitigation (1)
- conservation (1)
- convolutional neural networks (1)
- critical care (1)
- critically-ill patient (1)
- cross-ecosystem (1)
- data-oriented business process (1)
- de-agglomeration (1)
- deep learning (1)
- diesel (1)
- diesel emissions (1)
- diet specialization (1)
- disassembly plan (1)
- disassembly process (1)
- diuron (1)
- e-bikes (1)
- e-boards (1)
- ecological gradients (1)
- ecological niche models (1)
- edge detection (1)
- educational software (1)
- electric bus (1)
- electric conversion (1)
- electric kick scooters (1)
- electric light commercial vehicles (1)
- electric motorcycles (1)
- electric three- and four-wheelers (1)
- electric trucks (1)
- electric vehicles (1)
- electricity (1)
- embodied emissions (1)
- embodied impacts (1)
- emissions mitigation costs (1)
- energy (1)
- energy impacts (1)
- energy modeling (1)
- energy system (1)
- energy system modeling (1)
- energy use (1)
- environmental effect (1)
- environmental impact (1)
- eye fluke (1)
- fatigue properties (1)
- fed-batch (1)
- fed-batch fermentations (1)
- food web (1)
- frequency conversion (1)
- fuel cell vehicles (1)
- fungal growth (1)
- fungal pellets (1)
- fuzzy logic (1)
- genetic algorithm (1)
- global maps (1)
- health impact (1)
- heat (1)
- higher education for a sustainable development (1)
- higher education institutions (1)
- human-robot-collaboration (1)
- hybrid modelling (1)
- hydrochar (1)
- hydrothermal carbonization (1)
- image processing (1)
- image recognition (1)
- impact categories (1)
- indicator system (1)
- inferencing (1)
- informed software agent (1)
- insect communities (1)
- insects (1)
- intelligent robot assistant (1)
- intensive care (1)
- internal combustion engine vehicle (1)
- inversion twin (1)
- knowledge-intensive process (1)
- lab values (1)
- land cover (1)
- learning rates (1)
- light pollution (1)
- lightGBM (1)
- linear discriminant analysis (LDA) (1)
- local biodiversity (1)
- long‐term ecosystem research (1)
- mRNA-based vaccines (1)
- mRNA-vaccines (1)
- malaise trap (1)
- maximal function (1)
- mechanical testing (1)
- medical consumables (1)
- medical economics (1)
- medical informatics (1)
- meta-analysis (1)
- methanol analytics (1)
- methylotrophic organisms (1)
- microclimate (1)
- mobile phone (1)
- mobility impacts (1)
- model evaluation (1)
- monitoring (1)
- multimedia learning (1)
- multivariate curve resolution (1)
- near-surface temperatures (1)
- necroptosis (1)
- nonlinear diffusion (1)
- ontology (1)
- optical activity (1)
- optical rotatory dispersion (1)
- parasite (1)
- passenger cars (1)
- passenger kilometers travelled (1)
- pedagogical agent (1)
- pellets (1)
- per capita carbon footprint (1)
- photobioreactor (1)
- physics (1)
- pichia pastoris (1)
- plastics recycling (1)
- plug-in hybrid cars (1)
- plug-in hybrid electric vehicle (1)
- pollinator (1)
- power curve anomalies (1)
- power curve health value (1)
- predator-prey (1)
- problem drinking (1)
- process analytics (1)
- product model (1)
- protease inhibitor (1)
- radiative forcing (1)
- real-world driving (1)
- real-world emissions (1)
- real-world life-cycle inventory (1)
- reinforcement learning algorithm (1)
- repeated-batch fermentation (1)
- research infrastructure (1)
- robot system (1)
- second harmonic generation (1)
- self organizing maps (SOM) (1)
- septic cardiomyopathy (1)
- sharp function (1)
- single-use application (1)
- single‐use bioreactor (1)
- site networks (1)
- small data (1)
- smoking cessation (1)
- social norms (1)
- soft constraints (1)
- soil temperature (1)
- soil-dwelling organisms (1)
- sporulation conditions (1)
- stable isotope analysis (1)
- strategy (1)
- students (1)
- sustainability education (1)
- sustainable mobility (1)
- sustainable road transport (1)
- tar (1)
- temperature offset (1)
- tensile strength (1)
- terrestrial cyanobacteria (1)
- text messaging (1)
- thermal performance (1)
- time series classification (1)
- time trend (1)
- tobacco (1)
- toxic emissions (1)
- traffic emissions (1)
- traffic modes (1)
- transport (1)
- trap selectivity (1)
- uncertainty (1)
- urban mobility (1)
- vehicle mass (1)
- vehicle power (1)
- vehicle size effect (1)
- ventilation (1)
- virtual physics lab (1)
- weather stations (1)
- web (1)
- well-to-wheels (1)
- wind turbine (1)
- Ökologie (1)
- π–π interaction (1)
Institut
- FB Umweltplanung/-technik (UCB) (44) (entfernen)
Numerous research methods have been developed to detect anomalies in the areas of security and risk analysis. In healthcare, there are numerous use cases where anomaly detection is relevant. For example, early detection of sepsis is one such use case. Early treatment of sepsis is cost effective and reduces the number of hospital days of patients in the ICU. There is no single procedure that is sufficient for sepsis diagnosis, and combinations of approaches are needed. Detecting anomalies in patient time series data could help speed the development of some decisions. However, our algorithm must be viewed as complementary to other approaches based on laboratory values and physician judgments. The focus of this work is to develop a hybrid method for detecting anomalies that occur, for example, in multidimensional medical signals, sensor signals, or other time series in business and nature. The novelty of our approach lies in the extension and combination of existing approaches: Statistics, Self Organizing Maps and Linear Discriminant Analysis in a unique and unprecedented way with the goal of identifying different types of anomalies in real-time measurement data and defining the point where the anomaly occurs. The proposed algorithm not only has the full potential to detect anomalies, but also to find real points where an anomaly starts.
Purpose: The well-to-wheel (WTW) methodology is widely used for policy support in road transport. It can be seen as a simplified life cycle assessment (LCA) that focuses on the energy consumption and CO2 emissions only for the fuel being consumed, ignoring other stages of a vehicle’s life cycle. WTW results are therefore different from LCA results. In order to close this gap, the authors propose a hybrid WTW+LCA methodology useful to assess the greenhouse gas (GHG) profiles of road vehicles.
Methods: The proposed method (hybrid WTW+LCA) keeps the main hypotheses of the WTW methodology, but integrates them with LCA data restricted to the global warming potential (GWP) occurring during the manufacturing of the battery pack. WTW data are used for the GHG intensity of the EU electric mix, after a consistency check with the main life cycle impact (LCI) sources available in literature.
Results and discussion: A numerical example is provided, comparing GHG emissions due to the use of a battery electric vehicle (BEV) with emissions from an internal combustion engine vehicle. This comparison is done both according to the WTW approach (namely the JEC WTW version 4) and the proposed hybrid WTW+LCA method. The GHG savings due to the use of BEVs calculated with the WTW-4 range between 44 and 56 %, while according to the hybrid method the savings are lower (31–46 %). This difference is due to the GWP which arises as a result of the manufacturing of the battery pack for the electric vehicles.
Conclusions: The WTW methodology used in policy support to quantify energy content and GHG emissions of fuels and powertrains can produce results closer to the LCA methodology by adopting a hybrid WTW+LCA approach. While evaluating GHG savings due to the use of BEVs, it is important that this method considers the GWP due to the manufacturing of the battery pack.
Background: High numbers of consumable medical materials (eg, sterile needles and swabs) are used during the daily routine of intensive care units (ICUs) worldwide. Although medical consumables largely contribute to total ICU hospital expenditure, many hospitals do not track the individual use of materials. Current tracking solutions meeting the specific requirements of the medical environment, like barcodes or radio frequency identification, require specialized material preparation and high infrastructure investment. This impedes the accurate prediction of consumption, leads to high storage maintenance costs caused by large inventories, and hinders scientific work due to inaccurate documentation. Thus, new cost-effective and contactless methods for object detection are urgently needed.
Objective: The goal of this work was to develop and evaluate a contactless visual recognition system for tracking medical consumable materials in ICUs using a deep learning approach on a distributed client-server architecture.
Methods: We developed Consumabot, a novel client-server optical recognition system for medical consumables, based on the convolutional neural network model MobileNet implemented in Tensorflow. The software was designed to run on single-board computer platforms as a detection unit. The system was trained to recognize 20 different materials in the ICU, while 100 sample images of each consumable material were provided. We assessed the top-1 recognition rates in the context of different real-world ICU settings: materials presented to the system without visual obstruction, 50% covered materials, and scenarios of multiple items. We further performed an analysis of variance with repeated measures to quantify the effect of adverse real-world circumstances.
Results: Consumabot reached a >99% reliability of recognition after about 60 steps of training and 150 steps of validation. A desirable low cross entropy of <0.03 was reached for the training set after about 100 iteration steps and after 170 steps for the validation set. The system showed a high top-1 mean recognition accuracy in a real-world scenario of 0.85 (SD 0.11) for objects presented to the system without visual obstruction. Recognition accuracy was lower, but still acceptable, in scenarios where the objects were 50% covered (P<.001; mean recognition accuracy 0.71; SD 0.13) or multiple objects of the target group were present (P=.01; mean recognition accuracy 0.78; SD 0.11), compared to a nonobstructed view. The approach met the criteria of absence of explicit labeling (eg, barcodes, radio frequency labeling) while maintaining a high standard for quality and hygiene with minimal consumption of resources (eg, cost, time, training, and computational power).
Conclusions: Using a convolutional neural network architecture, Consumabot consistently achieved good results in the classification of consumables and thus is a feasible way to recognize and register medical consumables directly to a hospital’s electronic health record. The system shows limitations when the materials are partially covered, therefore identifying characteristics of the consumables are not presented to the system. Further development of the assessment in different medical circumstances is needed.
1. Recent reports on insect decline have highlighted the need for long-term data on insect communities towards identifying their trends and drivers.
2. With the launch of many new insect monitoring schemes to investigate insect communities over large spatial and temporal scales, Malaise traps have become one of the most important tools due to the broad spectrum of species collected and reduced capture bias through passive sampling of insects day and night. However, Malaise traps can vary in size, shape, and colour, and it is unknown how these differences affect biomass, species richness, and composition of trap catch, making it difficult to compare results between studies.
3. We compared five Malaise trap types (three variations of the Townes and two variations of the Bartak Malaise trap) to determine their effects on biomass and species richness as identified by metabarcoding.
4. Insect biomass varied by 20%–55%, not strictly following trap size but varying with trap type. Total species richness was 20%–38% higher in the three Townes trap models compared to the Bartak traps. Bartak traps captured lower richness of highly mobile taxa but increased richness of ground-dwelling taxa. The white roofed Townes trap captured a higher richness of pollinators.
5. We find that biomass, total richness, and taxa group specific richness are all sensitive to Malaise trap type. Trap type should be carefully considered and aligned to match monitoring and research questions. Additionally, our estimates of trap type effects can be used to adjust results to facilitate comparisons across studies.