Logo des Repositoriums

Auflistung nach Autor:in "Lepsien, Arvid"

1 - 3 von 3
  • Textdokument
    Describing Behavior Sequences of Fattening Pigs Using Process Mining
    (EMISA 2024, 2024) Lepsien, Arvid; Melfsen, Andreas; Bosselmann, Jan; Koschmider, Agnes; Hartung, Eberhard
    Process mining is a well-established technique for gaining insights into event data. It allows significant insights into event data in terms of identifying process anomalies, giving hints between as-is and to-be process states or making predictions based on data. Although process mining has been successfully applied in many application domains like healthcare, finance, and manufacturing, additional domains might also benefit from process mining like life and natural sciences. However, these domains mainly do not rely on structured business data that is expected as input for process mining algorithms. Rather, data from these domains first has to be efficiently pre-processed. This paper suggests process mining as an approach to identify behavioral patterns of fattening pigs from video data. The goal of this approach is to demonstrate that process mining might be a valuable tool for understanding the behavior of pigs by considering and analyzing their behavior sequences. Furthermore, additional insights can be gained in terms of temporal and spatial analysis about the division of the pig pen in functional areas. In this way, new implications might be found about pig behavior compared to existing state-of-the art approaches in the field.
  • Zeitschriftenartikel
    Künstliche Intelligenz für Tierwohl: Aktivitätserkennung und Process-Mining im Schweinestall
    (Wirtschaftsinformatik & Management: Vol. 15, No. 6, 2023) Lepsien, Arvid; Melfsen, Andreas; Koschmider, Agnes; Jäggle, Tobias
  • Konferenzbeitrag
    Process Mining for Unstructured Data: Challenges and Research Directions
    (Modellierung 2024, 2024) Koschmider, Agnes; Aleknonytė-Resch, Milda; Fonger, Frederik; Imenkamp, Christian; Lepsien, Arvid; Apaydin, Kaan; Janssen, Dominik; Langhammer, Dominic; Ziolkowski, Tobias; Zisgen, Yorck
    The application of process mining for unstructured data might significantly elevate novel insights into disciplines where unstructured data is a common data format. To efficiently analyze unstructured data by process mining and to convey confidence into the analysis result, requires bridging multiple challenges. The purpose of this paper is to discuss these challenges, present initial solutions and describe future research directions. We hope that this article lays the foundations for future collaboration on this topic.