Automatic time-series phenotyping using massive feature extraction

TL;DR

This paper introduces hctsa, a tool that automatically extracts and compares over 7700 features from time-series data, facilitating analysis across scientific fields by reducing manual effort and leveraging extensive prior research.

Contribution

The paper presents a novel automated feature extraction method for time-series data, enabling systematic analysis and interpretation across diverse scientific applications.

Findings

hctsa extracts over 7700 features from time series

demonstrated application in biological data analysis

improved understanding of time-series structure

Abstract

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.