Local Exceptionality Detection in Time Series Using Subgroup Discovery

Abstract

In this paper, we present a novel approach for local exceptionality detection on time series data. This method provides the ability to discover interpretable patterns in the data, which can be used to understand and predict the progression of a time series. This being an exploratory approach, the results can be used to generate hypotheses about the relationships between the variables describing a specific process and its dynamics. We detail our approach in a concrete instantiation and exemplary implementation, specifically in the field of teamwork research. Using a real-world dataset of team interactions we include results from an example data analytics application of our proposed approach, showcase novel analysis options, and discuss possible implications of the results from the perspective of teamwork research.

A Review of Using Wearable Technology to Assess Team Functioning and Performance

“…A general advice for researchers is to consider the modality of the measure, the pace of the physiological or behavioral process, the time scale of the task, and the available recording devices. Lastly, future research will benefit from developing a novel robust method that can reliably assess the coordination levels across modalities regardless of team size (e.g., Hudson et al, 2021), which would also be valuable for other fields besides team research (Delaherche et al, 2012). Ideally, these methods should not rely on dyadic models as they are computationally arduous, especially for larger teams.…”