Publications using hctsa
This page lists scientific research publications that have used hctsa.
Articles are labeled as follows:
📗 = Journal publication.
📙 = Preprint.
💻 = Link to GitHub code repository available.
If you have used hctsa in your published work, or we have missed any publications, feel free to reach out by email and we'll add it this growing list!
Our Research 📕
Methods Papers
The following publications for details of how the highly-comparative approach to time-series analysis has developed since our initial publication in 2013. We:
Reduced the hctsa feature library down to a reduced set of 22 efficiently coded features: catch22.
Developed a software package for highly-comparative time-series analysis, hctsa (includes applications to high throughput phenotyping of C. Elegans and Drosophila movement time series).
💻 Code (fly).
💻 Code (worm).
Introduced the feature-based time-series analysis methodology.
📗 Feature Engineering for Machine Learning and Data Analytics, CRC Press (2018).
Showed that the behaviour of thousands of time-series methods on thousands of different time series can be used to organise the interdisciplinary time-series analysis literature.
Applications Papers
We have used hctsa to:
Find dynamical signatures of psychiatric disorders from resting-state fMRI data.
Predict individual response to rTMS depression treatment from EEG data.
Distinguish meditators from non-meditators from 30s of resting-state EEG data.
Identify neurophysiological signatures of cortical micro-architecture.
Classify stars from NASA's Kepler Mission.
Determine how striatal neuromodulation affects brain dynamics in thalamus and cortex.
Uncover the dynamical structure of sleep EEG.
Show how gradients of variation in time-series properties of BOLD dynamics vary with physiological variation and structural connectivity in the human neocortex.
as well as:
Connect structural brain connectivity to fMRI dynamics (mouse).
Connect structural brain connectivity to fMRI dynamics (human).
Distinguish time-series patterns for data-mining applications.
Classify babies with low blood pH from fetal heart rate time series.
Others' Research 📕
🧬 Biology
Extract acoustic features from social vocal accommodation in adult marmoset monkeys.
Track Drosophila in real time for high-throughput behavioural phenotyping.
Detect anger from photoplethysmography (PPG) sensors.
Identify and distinguish marmoset vocalisations from audio, using Adaboost feature selection from hctsa features.
Discriminate zebra finch songs in different social contexts.
Distinguish electromagnetic field exposure from zebrafish locomotion time series.
🧫 Cellular Neuroscience
Confirm the role of µORs in VTA and NAc in acute fentanyl-induced behaviour (positive reinforcement).
Assess stress-induced changes in astrocyte calcium dynamics.
Assess the stress controllability of neurons from their activity time series.
🧠 Neuroimaging
Here are some highlights:
Understand changes in fMRI brain dynamics in patients with epilepsy.
Extract EEG markers of cognitive decline.
Detect EEG markers of seizure disorders.
Capture a distinctive fingerprint of an individual's resting-state fMRI data.
Identify methamphetamine users from EEG time series.
Compute temporal profile similarity for individual fingerprinting from human fMRI data.
Characterise subnetworks of the frontoparietal control network from fMRI recordings.
Find time-series properties of motor-evoked potentials that predict multiple sclerosis progression after two years.
Detect mild cognitive impairment using single-channel EEG to measure speech-evoked brain responses.
📗 IEEE Transactions on Neural Systems and Rehabilitation Engineering (2019).
In addition to:
Predict age from resting-state MEG from individual brain regions.
Estimate brain age in children from EEG.
Extract gradients from fMRI hctsa time-series features to understand the relationship between schizophrenia and nicotine dependence.
Classify endogenous (preictal), interictal, and seizure-like (ictal) activity from local field potentials (LFPs) from layers II/III of the primary somatosensory cortex of young mice (using feature selection methods from an initial pool of hctsafeatures).
Distinguish motor-evoked potentials corresponding to multiple sclerosis.
🔬 Medicine—General
Here are some highlights:
Differentiate tremor disorders using massive feature extraction, outperforming the best traditional tremor statistic.
Identify physiological features predictive of respiratory outcomes in extremely pre-term infants from bedside monitor data.
Discover signatures of fatal neonatal illness from vital signs.
Detect falls in elderly people from accelerometer data.
Prediction of post-cardiac arrest outcomes at discharge from physiological time series recorded on the first day of intensive care.
Detect falls of elderly people using wearable sensors.
Demonstrate that the suppression of essential tremor is due to a disruption of oscillations in the olivocerebellar loop.
Classify heartbeats measured using single-lead ECG.
Assess muscles for clinical rehabilitation.
in addition to:
Predict MS disability progression using time-series features of evoked potential signals
Identify sepsis in very low birth weight (<1.5kg) infants from heart rate signals, identifying heart rate characteristics of reduced variability and transient decelerations.
Identify novel heart-rate variability metrics, including
RobustSD, to create a parsimonious model for cerebral palsy prediction in preterm neonatal intensive care unit patients.Predicting post cardiac arrest outcomes.
Detect falls from wearable sensor data.
Detect falls from wearable sensor data.
Select features for fetal heart rate analysis using genetic algorithms.
🦠 Medicine—Pathology
Screen for COVID-19 using digital holographic microscopy.
Detect COVID-19 from red blood cells using digital holographic microscopy.
Identify the biogeographic heterogeneity of mucus, lumen, and feces.
🏗 Engineering
Here are some highlights:
Detect keyhole porosity formation during laser irradiation of Ti-6Al-4V substrates.
Identify keyhole pores in a laser powder-bed fusion process using acoustic and inline pyrometry time series.
Detect false data injection attacks into smart meters.
Predict pending loss of power stability from generator response signals.
Detect seeded bearing faults on a wind turbine subjected to non-stationary wind speed.
Recognise hand gestures.
Distinguish energy use behaviours from smart meter data.
Non-intrusively monitor load for appliance detection and electrical power saving in buildings.
Evaluate asphalt irregularity from smartphone sensors.
📗 International Symposium on Intelligent Data Analysis (2018).
in addition to:
Diagnose a spacecraft propulsion system utilizing data provided by the Prognostics and Health Management (PHM) society, as part of the Asia-Pacific PHM conference’s data challenge, 2023.
Identify faults in a large-scale industrial process.
⛰️ Geoscience
Detecting earthquakes from seismic recordings.
Find temporal patterns for reconstructing surface soil moisture time series.
Predict earthquakes (in the following month) from seismic indicators in Bangladesh.
Detect earthquakes in Groningen, The Netherlands.
📗 82nd EAGE Annual Conference & Exhibition Workshop Programme (2020).