A novel hybrid methodology for anomaly detection in time series

  • 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.

Download full text files

Export metadata

Metadaten
Author:Lejla Begic Fazlic, Ahmed Hallawa, Anke Schmeink, Robert Lipp, Lukas Martin, Arne Peine, Marlies Morgen, Thomas Vollmer, Stefan Winter, Guido Dartmann
URN:urn:nbn:de:hbz:tr5-1862
DOI:https://doi.org/10.1007/s44196-022-00100-w
Parent Title (English):International Journal of Computational Intelligence Systems
Publisher:Springer
Document Type:Article (specialist journals)
Language:English
Date of OPUS upload:2022/11/29
Date of first Publication:2022/07/22
Publishing University:Hochschule Trier
Release Date:2022/11/29
Tag:anomaly detection; classification; linear discriminant analysis (LDA); self organizing maps (SOM)
GND Keyword:Anomalieerkennung; Anomalie <Medizin>; Sepsis; Algorithmus; Selbstorganisierende Karte; Diskriminanzanalyse; Statistik
Volume:15
Issue:1
Article Number:50 (2022)
Page Number:16
First Page:1
Last Page:16
Departments:FB Umweltplanung/-technik (UCB)
Dewey Decimal Classification:0 Informatik, Informationswissenschaft, allgemeine Werke / 00 Informatik, Wissen, Systeme
Licence (German):License LogoCreative Commons - CC BY - Namensnennung 4.0 International