Logo des Repositoriums

Auflistung nach Schlagwort "expert system"

1 - 3 von 3
  • Konferenzbeitrag
    Evaluation of a decision support system for the recommendation of pasture harvest date and form
    (43. GIL-Jahrestagung, Resiliente Agri-Food-Systeme, 2023) Reuter, Tobias; Saborío Morales, Juan Carlos; Tieben, Christoph; Nahrstedt, Konstantin; Kraatz, Franz; Meemken, Hendrik; Hünker, Gerrit; Lingemann, Kai; Broll, Gabriele; Jarmer, Thomas; Hertzberg, Joachim; Trautz, Dieter
    The task of generating automatic recommendations of pasture harvest date and form was previously addressed through a knowledge-based decision support system (DSS). The system follows expert rules and exploits data such as the weather history and forecast, the growth stage of grass and legumes, plant height and crude fibre content. In this paper, we present the results of our evaluation of this DSS on 26 fields in West and Northwest Germany. We compared the suggestions made by the DSS with the decisions of expert farmers and obtained an accuracy of R²=0.746 and RMSE=7.83 days. The best results occurred for intensively managed fields for dairy cows, with an R² of 0.891 and RMSE of 3.20 days. We conclude our DSS and its underlying methodology have the potential to support farmers and secure high-quality fodder.
  • Konferenzbeitrag
    Online tool for matching company demands with IT-security offerings
    (Open Identity Summit 2022, 2022) Fähnrich, Nicolas; Roßnagel, Heiko
    Small and medium sized companies (SMEs) are often insufficiently protected against cyberattacks although there is a wide range of cybersecurity guidelines, products and services availableIn this paper, we present an online tool to support SMEs in improving their IT-security level by enabling them to identify critical business processes and to identify the most pressing protection needs by using a lightweight value chain-based approach. For using the online tool, no expert knowledge of the company’s IT-infrastructure or implemented IT-security measures is required, since no assessment of cybersecurity threats but of the impact of potential damage scenarios on business processes is carried out. Based on a generated set of recommendations, companies are provided with suitable IT-security measures and corresponding offerings in a prioritized order. These offerings include services and products to implement the given recommendations.
  • Textdokument
    Towards an Expert System for Identifying and Reducing Unnecessary Complexity of IT Architectures
    (INFORMATIK 2017, 2017) Wehling, Kenny; Schaefer, Ina
    Over the course of time, IT architectures in business environments grow and often include a range of different architectural variants. This causes various redundancies and a high level of IT complexity leading to higher costs and increased effort for evolving and maintaining the entire IT landscape. In this paper, we propose a concept for a rule based system that analyzes the variability within IT architectures automatically and supports experts in identifying and reducing the architecture’s complexity by eliminating unnecessary architectural variants.