Logo des Repositoriums

Auflistung nach Schlagwort "Uncertainty"

1 - 6 von 6
  • Konferenzbeitrag
    Architecture-based Propagation Analyses Regarding Security
    (Software Engineering 2024 (SE 2024), 2024) Hahner, Sebastian; Walter, Maximilian; Heinrich, Robert; Reussner, Ralf
  • Zeitschriftenartikel
    Characterisation of Large Changes in Wind Power for the Day-Ahead Market Using a Fuzzy Logic Approach
    (KI - Künstliche Intelligenz: Vol. 28, No. 4, 2014) Martínez-Arellano, Giovanna; Nolle, Lars; Cant, Richard; Lotfi, Ahmad; Windmill, Christopher
    Wind power has become one of the renewable resources with a major growth in the electricity market. However, due to its inherent variability, forecasting techniques are necessary for the optimum scheduling of the electric grid, specially during ramp events. These large changes in wind power may not be captured by wind power point forecasts even with very high resolution numerical weather prediction models. In this paper, a fuzzy approach for wind power ramp characterisation is presented. The main benefit of this technique is that it avoids the binary definition of ramp event, allowing to identify changes in power output that can potentially turn into ramp events when the total percentage of change to be considered a ramp event is not met. To study the application of this technique, wind power forecasts were obtained and their corresponding error estimated using genetic programming and quantile regression forests. The error distributions were incorporated into the characterisation process, which according to the results, improve significantly the ramp capture. Results are presented using colour maps, which provide a useful way to interpret the characteristics of the ramp events.
  • Zeitschriftenartikel
    Informationsunschärfe in Big Data
    (Wirtschaftsinformatik: Vol. 56, No. 5, 2014) Bendler, Johannes; Wagner, Sebastian; Brandt, Tobias; Neumann, Dirk
    Während die klassische Definition von Big Data ursprünglich nur die drei Größen Datenmenge (Volume), Datenrate (Velocity) und Datenvielfalt (Variety) umfasste, ist in jüngster Zeit der Wahrheitsgehalt (Veracity) als weitere Dimension mehr und mehr in den wissenschaftlichen und praktischen Fokus gerückt. Der noch immer wachsende Bereich der Sozialen Medien und damit verbundene benutzergenerierte Datenmengen verlangen nach neuen Methoden, die die enthaltene Datenunschärfe abschätzen und kontrollieren können. Dieser Beitrag widmet sich einem Aspekt der Datenunschärfe und stellt einen neuartigen Ansatz vor, der die Verlässlichkeit von benutzergenerierten Daten auf Basis von wiederkehrenden Mustern abschätzt. Zu diesem Zweck wird eine große Menge von Twitter-Statusnachrichten mit geographischer Standortinformation aus San Francisco untersucht und mit Points of Interest (POIs), wie beispielsweise Bars, Restaurants oder Parks, in Verbindung gebracht. Das vorgeschlagene Modell wird durch kausale Beziehungen zwischen Points of Interest und den in der Umgebung vorliegenden Twitter-Meldungen validiert. Weiterhin wird die zeitliche Dimension dieser Beziehung in Betracht gezogen, um so in Abhängigkeit der Art des POI wiederkehrende Muster zu identifizieren. Die durchgeführten Analysen münden in einem Indikator, der die Verlässlichkeit von vorliegenden Daten in räumlicher und zeitlicher Dimension abschätzt.AbstractWhile the classic definition of Big Data included the dimensions volume, velocity, and variety, a fourth dimension, veracity, has recently come to the attention of researchers and practitioners. The increasing amount of user-generated data associated with the rise of social media emphasizes the need for methods to deal with the uncertainty inherent to these data sources. In this paper we address one aspect of uncertainty by developing a new methodology to establish the reliability of user-generated data based upon causal links with recurring patterns. We associate a large data set of geo-tagged Twitter messages in San Francisco with points of interest, such as bars, restaurants, or museums, within the city. This model is validated by causal relationships between a point of interest and the amount of messages in its vicinity. We subsequently analyze the behavior of these messages over time using a jackknifing procedure to identify categories of points of interest that exhibit consistent patterns over time. Ultimately, we condense this analysis into an indicator that gives evidence on the certainty of a data set based on these causal relationships and recurring patterns in temporal and spatial dimensions.
  • Zeitschriftenartikel
    Many Facets of Reasoning Under Uncertainty, Inconsistency, Vagueness, and Preferences: A Brief Survey
    (KI - Künstliche Intelligenz: Vol. 31, No. 1, 2017) Kern-Isberner, Gabriele; Lukasiewicz, Thomas
    In this paper, we give an introduction to reasoning under uncertainty, inconsistency, vagueness, and preferences in artificial intelligence (AI), including some historic notes and a brief survey to previous approaches.
  • Konferenzbeitrag
    Orthogonal Uncertainty Model: Documenting Uncertainty in the Engineering of Cyber-Physical Systems
    (Software Engineering 2022, 2022) Bandyszak, Torsten; Daun, Marian; Tenbergen, Bastian; Kuhs, Patrick; Wolf, Stefanie; Weyer, Thorsten
    In this talk, we present our contribution ''Orthogonal Uncertainty Modeling in the Engineering of Cyber-Physical Systems'' published in IEEE Transactions on Automation Science and Engineering in July 2020 [Ba20]. We have proposed a modeling language for ''Orthogonal Uncertainty Models'' (OUMs). OUMs constitute a dedicated, central artifact to document, analyze, understand, and discuss potential uncertainties that may occur during operation. Thereby, OUMs support the systematic consideration of potential uncertainties the system might face during operation. OUMs allow documenting various aspects of uncertainty (e.g., cause and effect) in a dedicated artifact. Trace links are used to relate uncertainty to, e.g., system requirements across different model-based artifacts. We have applied OUMs to an industrial case study from the industry automation domain.
  • Zeitschriftenartikel
    Perception of an Uncertain Ethical Reasoning Robot
    (i-com: Vol. 18, No. 1, 2019) Stellmach, Hanna; Lindner, Felix
    This study investigates the effect of uncertainty expressed by a robot facing a moral dilemma on humans’ moral judgment and impression formation. In two experiments, participants were shown a video of a robot explaining a moral dilemma and suggesting a decision to make. The robot either expressed certainty or uncertainty about the decision it suggests. Participants rated how much blame the robot deserves for its decision, the moral wrongness of the chosen action, and their impression of the robot in terms of four scale dimensions measuring social perception. The results suggest that the subpopulation of participants unfamiliar with the moral dilemma assigns significantly more blame to the uncertain robot as compared to the certain one, while expressed uncertainty has less effect on moral wrongness judgments. The second experiment suggests that higher blame ratings are mediated by the fact that the uncertain robot was perceived as more humanlike. We discuss implications of this result for the design of social robots.