Logo des Repositoriums

Auflistung nach Autor:in "Janzen, Sabine"

1 - 4 von 4
  • Konferenzbeitrag
    Designing ubiquitous information systems based on conceptual models
    (INFORMATIK 2011 – Informatik schafft Communities, 2011) Janzen, Sabine; Filler, Andreas; Maass, Wolfgang
    Ubiquitous Information Systems (UIS) support single actors and groups by services over ubiquitous computing technologies anywhere and anytime. These systems require design approaches that keep a holistic view of situations in which single users and groups interact with one another and with accessible services. We introduce and exemplify the Situational Design Methodology for Information Systems (SiDIS) that uses three types of Conceptual Models (CMs) and corresponding translation procedures. This contribution focus on the specification and translation of the CMs as well as their processing by the resulting UIS.
  • Workshopbeitrag
    inSIDE Fair Dialogues: Assessing and Maintaining Fairness in Human-Computer-Interaction
    (Mensch und Computer 2018 - Workshopband, 2018) Janzen, Sabine; Bleymehl, Ralf; Alam, Aftab; Xu, Sascha; Stein, Hannah
    For simulating human-like intelligence in dialogue systems, individual and partially conflicting motives of interlocutors have to be processed in dialogue planning. Little attention has been given to this topic in dialogue planning in contrast to dialogues that are fully aligned with anticipated user motives. When considering dialogues with congruent and incongruent interlocutor motives like sales dialogues, dialogue systems need to find a balance between competition and cooperation. As a means for balancing such mixed motives in dialogues, we introduce the concept of fairness defined as combination of fair-ness state and fairness maintenance process. Focusing on a dialogue between human and robot in a retailing scenario, we show the application of the SatIsficing Dialogue Engine (inSIDE) - a platform for assessing and maintaining fairness in dialogues with mixed motives.
  • Konferenzbeitrag
    Mixed intention sets in dialogue planning
    (INFORMATIK 2013 – Informatik angepasst an Mensch, Organisation und Umwelt, 2013) Janzen, Sabine
    Non-collaborative dialogues are characterized by congruent and incongruent, partly conflicting intentions, that means mixed intention sets of the participants. Such dialogues are challenging for a number of reasons when supported by dialogue systems. We introduce a model of Situated Dialogue Action (SAM) that represents system-supported dialogues between multiple participants with mixed intention sets triggered by non-collaborative dialogue situations. Selected parts of SAM are instantiated by means of a Question-Answering (QA) system. We discuss our findings due to the instantiation in a QA setting and gave implications for future work.
  • Konferenzbeitrag
    Towards Energy-Efficient Large-Scale Artificial Intelligence for Sustainable Data Centers
    (INFORMATIK 2023 - Designing Futures: Zukünfte gestalten, 2023) Dokic, Dusan; Stein, Hannah; Janzen, Sabine; Maaß, Wolfgang
    The growing interest in AI services has led to a higher demand for computing power to train and execute complex AI models, causing a surge in power consumption in data centers. Together with rising costs for electricity, gas, petroleum, and coal, and the national target for climate neutrality of data centers by 2027, the ability to operate data centers economically is threatened in Germany. To address these issues, a pressing need to improve the sustainability of data centers and that of artificial intelligence. This paper proposes a roadmap to develop sustainable and resource-efficient data centers and AI systems. The roadmap includes four key building blocks: sustainable data centers, AI algorithms, AI sustainability framework, and economic efficiency analysis. Each building block poses pivotal research questions grounded in contemporary literature to guide the pursuit of environmental sustainability in data centers and AI.