2022/03/30 by Erik Jakobsson, Jakobsson, Erik, Erik Frisk +5
Computer Science · #Advanced Computational Techniques and Applications #Anomaly Detection Techniques and Applications #FOS: Electrical engineering #Signal Processing (eess.SP) #Time Series Analysis and Forecasting #electronic engineering #information engineering
paper · doi:10.48550/arxiv.2203.16121
openalex publication_date 2022/03/30 · openalex created_date 2022/05/05 · openalex updated_date 2026/07/28
In this work Time Series Classification techniques are investigated, and especially their applicability in applications where there are significant differences between the individuals where data is collected, and the individuals where the classification is evaluated. Classification methods are applied to a fault classification case, where a key assumption is that data from a fault free reference case for each specific individual is available. For the investigated application, wave propagation cause almost chaotic changes of a measured pressure signal, and physical modeling is difficult. Direct application of One-Nearest-Neighbor Dynamic Time Warping, a common technique for this kind of problem, and other machine learning techniques are shown to fail for this case and new methods to improve the situation are presented. By using relative features describing the difference from the reference case rather than the absolute time series, improvements are made compared to state-of-the-art time series classification algorithms.