Automatic time-series phenotyping using massive feature extraction

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.

Cited by in corpus (27)

• Benchmarking Multivariate Time Series Classification Algorithms
• HIVE-COTE 2.0: a new meta ensemble for time series classification
• sktime: A Unified Interface for Machine Learning with Time Series
• Bake off redux: a review and experimental evaluation of recent time series classification algorithms
• The Canonical Interval Forest (CIF) Classifier for Time Series Classification
• Global-scale massive feature extraction from monthly hydroclimatic time series: Statistical characterizations, spatial patterns and hydrological similarity
• The FreshPRINCE: A Simple Transformation Based Pipeline Time Series Classifier
• Classifying Kepler light curves for 12,000 A and F stars using supervised feature-based machine learning
• Massive feature extraction for explaining and foretelling hydroclimatic time series forecastability at the global scale
• Unsupervised Feature Based Algorithms for Time Series Extrinsic Regression
• A Physiology-Driven Computational Model for Post-Cardiac Arrest Outcome Prediction
• Tracking the distance to criticality in systems with unknown noise
• Feature engineering workflow for activity recognition from synchronized inertial measurement units
• Hydroclimatic time series features at multiple time scales
• Subtyping patients with chronic disease using longitudinal BMI patterns
• Spikebench: An open benchmark for spike train time-series classification
• Automatic Feature Engineering for Time Series Classification: Evaluation and Discussion
• Finding binaries from phase modulation of pulsating stars with \textit{Kepler}: VI. Orbits for 10 new binaries with mischaracterised primaries
• Peptide Classification from Statistical Analysis of Nanopore Translocation Experiments
• Forecasting with sktime: Designing sktime's New Forecasting API and Applying It to Replicate and Extend the M4 Study
• CompEngine: a self-organizing, living library of time-series data
• Monash Time Series Forecasting Archive
• Revisit Time Series Classification Benchmark: The Impact of Temporal Information for Classification
• Identifying statistical indicators of temporal asymmetry using a data-driven approach
• Time series features for supporting hydrometeorological explorations and predictions in ungauged locations using large datasets
• On-site Online Feature Selection for Classification of Switchgear Actuations
• Winning with Simple Learning Models: Detecting Earthquakes in Groningen, the Netherlands