Logo des Repositoriums

Auflistung nach Schlagwort "Transformer"

1 - 2 von 2
  • Konferenzbeitrag
    Anomaly Detection in Supermarket Refrigeration Systems using Transformer Models: A Comparative Study
    (INFORMATIK 2024, 2024) Meyer, Melina; Gergeleit, Martin; Krechel, Dirk
    This study investigates anomaly detection methods in supermarket refrigeration systems. A transformer-based model is introduced in this field and compared with LSTM autoencoders. The models are trained and evaluated using preprocessed refrigeration data, with parameters optimized for accuracy, recall, precision, and F1 score. Our findings aim to enhance system monitoring and maintenance strategies, ultimately improving reliability, energy efficiency, and operational excellence in supermarket refrigeration technology.
  • Konferenzbeitrag
    Der Einsatz von Neural Language Models für eine barrierefreie Verwaltungskommunikation: Anforderungen an die automatisierte Vereinfachung rechtlicher Informationstexte
    (6. Fachtagung Rechts- und Verwaltungsinformatik (RVI 2023), 2023) Gille, Michael; Schomacker, Thorben; von der Hülls, Jörg; Tropmann-Frick, Marina
    Machine-learning-based text simplification can be used to meet legal obligations to provide comprehensibility-enhanced public service texts. The article examines the use of artificial intelligence for public administration communication in rule-based easy language. The authors outline essential technical, legal and normative requirements for the development and use of automated text simplification through neural language generation. As part of the Open-LS research project, a contribution is made to clarifying the possibilities and limits of the use of artificial intelligence systems for text simplification in public services.