# Automatic time-series phenotyping using massive feature extraction

arXiv: https://arxiv.org/abs/1612.05296 · HTML: https://mlsanity.com/paper/1612.05296/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 15 Dec 2016.

## Built on by (most cited first, 12 of 12)

- [Monash Time Series Forecasting Archive](https://mlsanity.com/paper/2105.06643/) (2021)
- [HIVE-COTE 2.0: a new meta ensemble for time series classification](https://mlsanity.com/paper/2104.07551/) (2021)
- [Forecast combinations: an over 50-year review](https://mlsanity.com/paper/2205.04216/) (2022)
- [Massive feature extraction for explaining and foretelling hydroclimatic time series forecastability at the global scale](https://mlsanity.com/paper/2108.00846/) (2021)
- [Novel Features for Time Series Analysis: A Complex Networks Approach](https://mlsanity.com/paper/2110.09888/) (2021)
- [Class-Specific Explainability for Deep Time Series Classifiers](https://mlsanity.com/paper/2210.05411/) (2022)
- [An Empirical Evaluation of Time-Series Feature Sets](https://mlsanity.com/paper/2110.10914/) (2021)
- [Time series features for supporting hydrometeorological explorations and predictions in ungauged locations using large datasets](https://mlsanity.com/paper/2204.06540/) (2022)
- [AutoFITS: Automatic Feature Engineering for Irregular Time Series](https://mlsanity.com/paper/2112.14806/) (2021)
- [Hydroclimatic time series features at multiple time scales](https://mlsanity.com/paper/2112.01447/) (2021)
- [Automated Mobility Context Detection with Inertial Signals](https://mlsanity.com/paper/2205.08409/) (2022)
- [fETSmcs: Feature-based ETS model component selection](https://mlsanity.com/paper/2206.12882/) (2022)

## Abstract (arXiv)

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.