Logo des Repositoriums

Auflistung nach Schlagwort "Human-in-the-loop"

1 - 2 von 2
  • Konferenzbeitrag
    Enhancing Human-in-the-Loop Adaptive Systems through Digital Twins and VR Interfaces
    (Software Engineering 2022, 2022) Yigitbas, Enes; Karakaya, Kadiray; Jovanovikj, Ivan; Engels, Gregor
    This work has been published as a full paper at SEAMS'21. In the context of self-adaptive systems, there are situations where human involvement in the adaptation process is beneficial or even necessary. For such ''human-in-the-loop'' adaptive systems, two major challenges, namely transparency, and controllability must be addressed to include the human in the self-adaptation loop. Transparency covers the context information about the adaptive system and its context while controllability targets the decision-making and adaptation operations. As existing human-in-the-loop adaptation approaches do not fully cover these aspects, we investigate alternative human-in-the-loop strategies by using a combination of digital twins and virtual reality (VR) interfaces. Based on the concept of the digital twin, we represent a self-adaptive system and its respective context in a virtual environment. For integrating the human in the decision-making and adaptation process, we have implemented and analyzed two different human-in-the-loop strategies in VR: a procedural control where the human can control the decision making-process and adaptations through VR interactions and a declarative control where the human specifies the goal state and the configuration is delegated to an AI planner. We evaluate our approach based on an autonomic robot system that is accessible through a VR interface.
  • Zeitschriftenartikel
    Identification of Explainable Structures in Data with a Human-in-the-Loop
    (KI - Künstliche Intelligenz: Vol. 36, No. 0, 2022) Thrun, Michael C.
    Explainable AIs (XAIs) often do not provide relevant or understandable explanations for a domain-specific human-in-the-loop (HIL). In addition, internally used metrics have biases that might not match existing structures in the data. The habilitation thesis presents an alternative solution approach by deriving explanations from high dimensional structures in the data rather than from predetermined classifications. Typically, the detection of such density- or distance-based structures in data has so far entailed the challenges of choosing appropriate algorithms and their parameters, which adds a considerable amount of complex decision-making options for the HIL. Central steps of the solution approach are a parameter-free methodology for the estimation and visualization of probability density functions (PDFs); followed by a hypothesis for selecting an appropriate distance metric independent of the data context in combination with projection-based clustering (PBC). PBC allows for subsequent interactive identification of separable structures in the data. Hence, the HIL does not need deep knowledge of the underlying algorithms to identify structures in data. The complete data-driven XAI approach involving the HIL is based on a decision tree guided by distance-based structures in data (DSD). This data-driven XAI shows initial success in the application to multivariate time series and non-sequential high-dimensional data. It generates meaningful and relevant explanations that are evaluated by Grice’s maxims.