Structural and Semantic Data Layers in Time Series Analyses

Alexander Graß, Christian Beecks, Stefan Decker

Abstract: Understanding the inherent complexity of temporal data is crucial for effective time series analytics. One dimension of complexity is the level of structural depth at which analysis methods operate. These levels range from entire time series collections down to individual sequences of reduced dimensionality and length. Complementary to this type of complexity, is the quantity and expressiveness of knowledge associated with time series data, including labels and other features that provide valuable information. Both, the structural as well as the semantic layer, define the suitability and effectiveness of different analysis methods. In this paper we introduce a conceptual framework to support the automated selection of analytical time series approaches. To this end, we specify a context-free grammar to describe hierarchies and compositions of time series data, while also defining different classes of semantic information, resulting in a data-specific classification of time series analysis methods. Along with a demonstration via concrete examples, we provide a discussion on challenges, opportunities and future work associated with the proposed approach.