TY - JOUR A1 - Begic Fazlic, Lejla A1 - Hallawa, Ahmed A1 - Schmeink, Anke A1 - Lipp, Robert A1 - Martin, Lukas A1 - Peine, Arne A1 - Morgen, Marlies A1 - Vollmer, Thomas A1 - Winter, Stefan A1 - Dartmann, Guido T1 - A novel hybrid methodology for anomaly detection in time series T2 - International Journal of Computational Intelligence Systems N2 - Numerous research methods have been developed to detect anomalies in the areas of security and risk analysis. In healthcare, there are numerous use cases where anomaly detection is relevant. For example, early detection of sepsis is one such use case. Early treatment of sepsis is cost effective and reduces the number of hospital days of patients in the ICU. There is no single procedure that is sufficient for sepsis diagnosis, and combinations of approaches are needed. Detecting anomalies in patient time series data could help speed the development of some decisions. However, our algorithm must be viewed as complementary to other approaches based on laboratory values and physician judgments. The focus of this work is to develop a hybrid method for detecting anomalies that occur, for example, in multidimensional medical signals, sensor signals, or other time series in business and nature. The novelty of our approach lies in the extension and combination of existing approaches: Statistics, Self Organizing Maps and Linear Discriminant Analysis in a unique and unprecedented way with the goal of identifying different types of anomalies in real-time measurement data and defining the point where the anomaly occurs. The proposed algorithm not only has the full potential to detect anomalies, but also to find real points where an anomaly starts. KW - anomaly detection KW - classification KW - self organizing maps (SOM) KW - linear discriminant analysis (LDA) KW - Anomalieerkennung KW - Anomalie KW - Sepsis KW - Algorithmus KW - Selbstorganisierende Karte KW - Diskriminanzanalyse KW - Statistik Y1 - 2022 UR - https://hst.opus.hbz-nrw.de/frontdoor/index/index/docId/186 UR - https://nbn-resolving.org/urn:nbn:de:hbz:tr5-1862 VL - 15 IS - 1 SP - 1 EP - 16 PB - Springer ER -