Suche
Anzeige der Dokumente 21-30 von 39
Aufsatz
3DWoodWind: robotic winding processes for material-efficient lightweight veneer components
(2022-03-25)
Winding processes are known from fiber composite technology for highly resistance lightweight components for aviation. These fiber-based processes work predominantly with synthetic composites made of carbon or glass fibers. For the construction industry, these additive processes are very promising and resource-efficient building processes, but they are still hardly used in timber construction despite the very high level of digitalization and technical development. The 3DWoodWind research project uses a continuous ...
Aufsatz
Stream-based active learning for sliding windows under the influence of verification latency
(2021-11-18)
Stream-based active learning (AL) strategies minimize the labeling effort by querying labels that improve the classifier’s performance the most. So far, these strategies neglect the fact that an oracle or expert requires time to provide a queried label. We show that existing AL methods deteriorate or even fail under the influence of such verification latency. The problem with these methods is that they estimate a label’s utility on the currently available labeled data. However, when this label would arrive, some of ...
Aufsatz
CLeaR: An adaptive continual learning framework for regression tasks
(2021-07-16)
Catastrophic forgetting means that a trained neural network model gradually forgets the previously learned tasks when being retrained on new tasks. Overcoming the forgetting problem is a major problem in machine learning. Numerous continual learning algorithms are very successful in incremental learning of classification tasks, where new samples with their labels appear frequently. However, there is currently no research that addresses the catastrophic forgetting problem in regression tasks as far as we know. This ...
Aufsatz
Vertrauen und Führung im Kontext digitaler Arbeit
(2020-04-16)
Der vorliegende Beitrag der Zeitschrift „Gruppe. Interaktion. Organisation. (GIO)“ untersucht die Relevanz von Vertrauen zwischen Führungskraft und Mitarbeiter im Kontext der Digitalisierung und kommt zu dem Ergebnis, dass Vertrauen in Zukunft noch bedeutsamer wird. Der Beitrag gelangt zu dieser Erkenntnis, indem er die psycho-sozialen Auswirkungen der Digitalisierung auf organisationaler Ebene identifiziert und systematisch die möglichen Wirkzusammenhänge zu Vertrauen analysiert. Die Analyse ergibt, dass sich die ...
Aufsatz
A Hybrid Optimization Method Combining Network Expansion Planning and Switching State Optimization
(2020-07-01)
Combining switching state optimization (SSO) and network expansion planning (NEP) in AC systems results in a mixed-integer non-linear optimization problem. Two methodically different solution approaches are mathematical programming and heuristic methods. In this paper, we develop a hybrid optimization method combining both methods to solve the combined optimization of SSO and NEP. The presented hybrid method applies a DC programming model as an initialization strategy to reduce the search space of the heuristic. A ...
Aufsatz
Virtual Reality Experience of Mega Sports Events: A Technology Acceptance Study
(2022-05-24)
Digitalization has advanced to become an opportunity to spectate sports during the pandemic and its restrictions for traveling to competitions. The purpose of this study is to investigate the antecedents of using virtual reality technology for spectating mega sports events. Based on a literature review, the authors created a model of behavioral intention, built on the unified theory of acceptance and use of technology and technology acceptance model to examine the curiosity and self-construal of spectators. An online ...
Aufsatz
Knowledge cores in large formal contexts
(2022-04-20)
Knowledge computation tasks, such as computing a base of valid implications, are often infeasible for large data sets. This is in particular true when deriving canonical bases in formal concept analysis (FCA). Therefore, it is necessary to find techniques that on the one hand reduce the data set size, but on the other hand preserve enough structure to extract useful knowledge. Many successful methods are based on random processes to reduce the size of the investigated data set. This, however, makes them hardly ...
Aufsatz
A combined FD-HB approximation method for steady-state vibrations in large dynamical systems with localised nonlinearities
(2022-09-21)
The approximation of steady-state vibrations within non-linear dynamical systems is well-established in academics and is becoming increasingly important in industry. However, the complexity and the number of degrees of freedom of application-oriented industrial models demand efficient approximation methods for steady-state solutions. One possible approach to that problem are hybrid approximation schemes, which combine advantages of standard methods from the literature. The common ground of these methods is their ...
Aufsatz
On the Automation of Flood Event Separation From Continuous Time Series
(2020-07-28)
Can machine learning effectively lower the effort necessary to extract important information from raw data for hydrological research questions? On the example of a typical water-management task, the extraction of direct runoff flood events from continuous hydrographs, we demonstrate how machine learning can be used to automate the application of expert knowledge to big data sets and extract the relevant information. In particular, we tested seven different algorithms to detect event beginning and end solely from a ...
Aufsatz
Unterstützung digitaler Bildungsprozesse durch interaktive gamifizierte Lernvideos – Wie innovative Lernvideos Motivation und Lernerfolg steigern können
(2021-10-11)
Digitales Lernen ist ein zentraler Bestandteil der heutigen Bildungslandschaft geworden. Insbesondere Lernvideos haben in den letzten Jahren deutlich an Popularität gewonnen und Plattformen wie YouTube sind heute ein fester Bestandteil von Lernprozessen. Bildungseinrichtungen haben diese Entwicklung erkannt und Lernvideos in ihre Lernsysteme integriert. Allerdings sind die heutigen Lernvideos oft nicht sehr ansprechend, weil es an Gestaltungswissen mangelt, wie Interaktionen und gamifizierte Elemente die Motivation ...