Automatic time-series phenotyping using massive feature extraction
This tool addresses the time-consuming and non-systematic process of feature extraction in time-series analysis for scientific and industrial applications, though it is incremental as it builds on existing features.
The paper tackles the problem of manually devising time-series features for analysis by introducing hctsa, a tool that automatically selects interpretable properties from over 7700 features, enabling researchers to quantify structure in time-series data efficiently.
Across a far-reaching diversity of scientific and industrial applications, a general key problem involves relating the structure of time-series data to a meaningful outcome, such as detecting anomalous events from sensor recordings, or diagnosing patients from physiological time-series measurements like heart rate or brain activity. Currently, researchers must devote considerable effort manually devising, or searching for, properties of their time series that are suitable for the particular analysis problem at hand. Addressing this non-systematic and time-consuming procedure, here we introduce a new tool, hctsa, that selects interpretable and useful properties of time series automatically, by comparing implementations over 7700 time-series features drawn from diverse scientific literatures. Using two exemplar biological applications, we show how hctsa allows researchers to leverage decades of time-series research to quantify and understand informative structure in their time-series data.