Logo des Repositoriums

Band 45 - Heft 5 (Oktober 2022)

Autor*innen mit den meisten Dokumenten  

Auflistung nach:

Neueste Veröffentlichungen

1 - 10 von 18
  • Zeitschriftenartikel
    Publisher Erratum: Mitteilungen der GI im Informatik Spektrum 4/2022
    (Informatik Spektrum: Vol. 45, No. 5, 2022) Winter, Cornelia
  • Zeitschriftenartikel
    Cross domain fusion for spatiotemporal applications: taking interdisciplinary, holistic research to the next level
    (Informatik Spektrum: Vol. 45, No. 5, 2022) Renz, Matthias; Kröger, Peer; Koschmider, Agnes; Landsiedel, Olaf; Tavares de Sousa, Nelson
    Exploiting the power of collective use of complementing data sources for the discovery of new correlations and findings offers enormous additional value compared to the summed values of isolated analysis of the individual information sources. In this article, we will introduce the concept of “cross domain fusion” (CDF) as a machine learning and pattern mining driven and multi-disciplinary research approach for fusing data and knowledge from a variety of sources enabling the discovery of answers of the question to be examined from a more complete picture. The article will give a basic introduction in this emerging field and will highlight examples of basic CDF tasks in the field of marine science.
  • Zeitschriftenartikel
    Um etliche Ecken ged8
    (Informatik Spektrum: Vol. 45, No. 5, 2022) Windenberg, Rolf
  • Zeitschriftenartikel
    Cross-domain fusion in smart seafloor sensor networks
    (Informatik Spektrum: Vol. 45, No. 5, 2022) Zainab, Tayyaba; Karstens, Jens; Landsiedel, Olaf
    Many of the socio-economic and environmental challenges of the 21st century like the growing energy and food demand, rising sea levels and temperatures put stress on marine ecosystems and coastal populations. This requires a significant strengthening of our monitoring capacities for processes in the water column, at the seafloor and in the subsurface. However, present-day seafloor instruments and the required infrastructure to operate these are expensive and inaccessible. We envision a future Internet of Underwater Things, composed of small and cheap but intelligent underwater nodes. Each node will be equipped with sensing, communication, and computing capabilities. Building on distributed event detection and cross-domain data fusion, such an Internet of Underwater Things will enable new applications. In this paper, we argue that to make this vision a reality, we need new methodologies for resource-efficient and distributed cross-domain data fusion. Resource-efficient, distributed neural networks will serve as data-analytics pipelines to derive highly aggregated patterns of interest from raw data. These will serve as (1) a common base in time and space for fusion of heterogeneous data, and (2) be sufficiently small to be transmitted efficiently in resource-constrained settings.
  • Zeitschriftenartikel
    Cross domain fusion in power electronics dominated distribution grids
    (Informatik Spektrum: Vol. 45, No. 5, 2022) Sante, Pugliese; Landsiedel, Olaf; Kuprat, Johannes; Liserre, Marco
    In the near future, a drastic change in the structure of the electric grid is expected due to the increasing penetration of power electronics interfaced renewable energy sources (e.g. solar and wind), highly variable loads (e.g. electric vehicles and air conditioning) and unexpected energy demanding events (e.g. pandemics or natural disasters). Energy balancing management, voltage and frequency stability, reduced system inertia, grid resilience to fault conditions, and power quality of the supply are a few of the main challenges in the future power electronics dominated grids. Power electronics can solve these by integrating information and communication technology in new intelligent, highly reliable, and efficient devices like smart transformers. Smart transformers can increase the power flow flexibility by enabling the correct meshed-hybrid grid operations, as long as load mission and power generation profiles are known. Those profile are generally driven by heterogeneous, highly sparse and often incomplete data that belong to different domains. This article highlights the necessity of new approaches and models to identify patterns and events of interest that can serve as a common base. The resulting patterns can then be cross-fused in a common language and form the basis of further data analytics in future distribution grids.
  • Zeitschriftenartikel
    Modularizing Earth system models for interactive simulation
    (Informatik Spektrum: Vol. 45, No. 5, 2022) Claus, Martin; Gundlach, Sven; Hasselbring, Wilhelm; Jung, Reiner; Rath, Willi; Schnoor, Henning
    Interactive exploration of Earth system simulations may have great potential to improve the scientific modeling process. It will allow monitoring of the state of the simulation via dashboards presenting real-time diagnostics within a digital twin world. We present the state of the art for Earth system modeling in this context. Cross-domain data handling and fusion will make it possible to integrate model and observation data in the context of digital twins of the ocean. Domain-driven modularization of monolithic Earth system models allows one to recover interfaces for such a cross-domain fusion. Reverse engineering with static and dynamic analysis enables modularization of Earth system models. The modularization does not only help with restructuring existing Earth system models, it also makes it possible to integrate additional scientific domains into the interactive simulation environment.
  • Zeitschriftenartikel
    Can neural networks predict steady annual cycles of marine ecosystems?
    (Informatik Spektrum: Vol. 45, No. 5, 2022) Slawig, Thomas; Pfeil, Markus
    We used artificial neural networks to replace the complete spin-up procedure that computes a steady annual cycle of a marine ecosystem driven by ocean transport. The networks took only the few biogeochemical model parameters and attempted to predict the spatially distributed concentrations of the ecosystem, in this case only nutrients, for one time point of the annual cycle. The ocean circulation was fixed for all parameters. Different network topologies, sparse networks, and hyperparameter optimization using a genetic algorithm were used. This showed that all studied networks can produce a distribution that is point-wise close to the original spin-up result. However, these predictions were far from being annually periodic, such that a subsequent spin-up was necessary. In this way, the overall runtime of the spin-up could be reduced by 13% on average. It is debatable whether this procedure is useful for the generation of initial values, or whether simpler methods can achieve faster convergence. Wir haben künstliche neuronale Netze verwendet, um den kompletten Spin-up zu ersetzen, mit dem ein stetiger Jahreszyklus eines marinen, durch den Ozeantransport angetriebenen Ökosystems berechnet wird. Die Netze nahmen nur die wenigen biogeochemischen Modellparameter und versuchten, die räumlich verteilten Konzentrationen des Ökosystems, hier nur Nährstoffe, für einen Zeitpunkt des Jahreszyklus vorherzusagen. Die Ozeanzirkulation war für alle Parameter fest. Es wurden verschiedene Netzwerktopologien, „sparse networks“ und ein Hyperparametertuning durch einen genetischen Algorithmus verwendet. Alle Netze konnten eine Verteilung erzeugen, die dem ursprünglichen Spin-up-Ergebnis punktweise ähnlich war. Allerdings waren die Vorhersagen weit davon entfernt, jahresperiodisch zu sein, weshalb ein nachträglicher Spin-up nötig war. So konnte die Gesamtlaufzeit des Spin-ups im Durchschnitt um 13 % reduziert werden. Es bleibt fraglich, ob dieses Verfahren sinnvoll ist, um Anfangswerte zu generieren, oder ob einfachere Methoden eine schnellere Konvergenz erreichen können.
  • Zeitschriftenartikel
    Reinforcement learning as a basis for cross domain fusion of heterogeneous data
    (Informatik Spektrum: Vol. 45, No. 5, 2022) Christensen, Sören; Tomforde, Sven
    We propose to establish a research direction based on Reinforcement Learning in the scope of Cross Domain Fusion. More precisely, we combine the algorithmic approach of evolutionary rule-based Reinforcement Learning with the efficiency and performance of Deep Reinforcement Learning, while simultaneously developing a sound mathematical foundation. A possible scenario is traffic control in urban regions.
  • Zeitschriftenartikel
    Cross Domain Fusion in der Archäologie – Interview mit Dr. Michael Kempf und Prof. Dr. Oliver Nakoinz
    (Informatik Spektrum: Vol. 45, No. 5, 2022) Renz, Matthias; Strohm, Steffen; Kempf, Michael; Nakoinz, Oliver
  • Zeitschriftenartikel
    (Informatik Spektrum: Vol. 45, No. 5, 2022) Lenz, Hans-J.