Publications using catch22

This is a list of publications using catch22. Please get in touch by email if we've missed a paper of yours!

Publications

Algorithms

catch22 features have formed the basis of new algorithms:

• As a basis for developing semi-synthetic time series to understand algorithm performance 📙 arXiv (2023).
• A new method to reduce the complexity of feature-based explanations. 📗 Information Fusion (2023).
• The canonical interval time-series classifier. 📗 IEEE International Conference on Big Data (2020).

Applications

catch22 features have been used in applications to:

Physiological and other sensors

• Classify hyperkinetic, tonic, and tonic-clonic seizures using unsupervised clustering of video signals. 📗 Frontiers in Neurology (2023).
• Estimate pain intensity from physiological sensors. 📙 arXiv (2023).
• Classify human exercises using wearable sensors and video data 📗 Joint European Conference on Machine Learning and Knowledge Discovery in Databases (2023).
• Classify advertising engagement using affect and physiological signals of heart rate, electrodermal activity, pupil dilation, and skin temperature 📗 Sensors (2023).
• Video-based approach for human exercise classification 📙 arXiv (2023).
• Determine the type of breathing using wireless sensors with a motion capture system 📗 Algorithms (2023).
• Distinguishing types of human breathing from motion-capture data 📗 Algorithms (2023).
• Automate General Movements Assessment for Cerebral Palsy from smartphone videos. 📙 medRxiv (2023).
• Detect stress levels in real time from multiple physiological signals (heart rate, blood pressure, electrodermal activity, and respiration). 📗 IEEE Access (2023).
• Comparison to ShapAAL method for sensor time-series classification. 📗 PLoS ONE (2022).
• Extract markers of cardiometabolic disease risk from wearable device recordings. 📗 Journal of Medical Internet Research (2022).
• Predict behavioral change from physiological signals. 📗 Sensors (2022).
• Estimate objective pain intensity using catch22 features computed from physiological sensors, paving the way for developing a wearable pain measurement device. 📗 PLoS ONE (2021).

Biology, neuroscience, pathology, and ecology

• Predict the incidence trends of infectious diseases. BMC Bioinformatics (2024).
• Distinguish chemical stimuli from C. elegans chemosensory system recordings. 📙 bioRxiv (2024).
• Predict when an individual patient can switch from intravenous to oral antibiotic treatment from routinely collected clinical parameters from over 10,000 intensive care unit stays. 📗 Nature Communications (2024).
• Track Drosophila in real time for high-throughput behavioral phenotyping. 📗 eLife (2023).
• Evaluate similarity of synthetically generated peripheral nerve signals 📗 10th International IEEE/EMBS Conference on Neural Engineering (NER) (2021).
• Demonstrate that oxygen consumption rate time-series measurements are highly predictive of cardiomyocytes differentiation outcome from human-induced pluripotent stem cells 📗 Biotechnology and Bioengineering (2023).
• Detect dynamic electrical signatures of human breast cancer cells from voltage imaging. 📗 Communcations Biology (2022).
• Screen for COVID-19 using holographic microscopy reconstructed red blood cells. 📗 Biomedical Optics Express (2022).
• Understand influences on the dynamics of tree motion. 📗 Biogeosciences (2021).

Industry, energy, and chemistry

• Component identification for intelligent devices. 📙 2023 IEEE International Conference on Data Mining Workshops (ICDMW).
• Detect edge flag faults in wind turbines. 📗 Wind Energ. Sci. Discuss. (2023).
• Compare the influence of imputation strategies for classfying household devices from electricity usage. 📗 2023 Tenth International Conference on Social Networks Analysis, Management and Security (SNAMS) (2024).
• Active trailing edge flap system fault detection in wind turbines 📗 Wind Energ. Sci. Discuss. (2023).
• Detect chemical analytes from chemiresistive hardware sensor arrays 📙 arXiv (2023).
• Detect fraud from smart meters 📗 Journal of Internet Services and Applications (2023).
• Appliance detection from very low-frequency smart meter time series 📙 ResearchGate (2023).
• Track on-board diagnostics for monitoring engine operations. 📗 Proceedings of the 8th International Conference on Vehicle Technology and Intelligent Transport Systems - VEHITS (2022).
• Detect anomalies in cloud services, where using catch22 resulted in the highest performance. 📗 IoT (2022).
• Predict anode effects in aluminium production at least 1 min in advance from TRIMET Aluminium SE Essen (TAE) time-series data. 📗 Applied Sciences (2021).

Neuroimaging

• EEG Signal Classification using Genetic Programming-based AutoML 📙 Journal of Information and Data Management (2024).
• EEG classification using AutoML 📙 Anais do Symposium on Knowledge Discovery, Mining and Learning (KDMiLe) (2023).
• Infer rules underlying experience of subjective liking of artwork stimuli from EEG 📗 PLoS ONE (2023).
• Identify methamphetamine users from EEG data 📙 ResearchGate (2023).

Meteorology and astronomy

• Generate long-term air temperature forecasts as part of explainable AI models. 📗 Atmospheric Research (2023).
• Detect earthquakes. 📙 arXiv (2022).
• Classify exoplanets using catch22 features extracted from their light curves. 📙 Student dissertation (2019).

Finance and databases

• As part of an algorithm for metalearning to predict movement of financial markets. 📙 Journal of Information and Data Management (2024).
• Representations for time series in database management systems, such as Apache IoTDB, InfluxDB, OpenTSDB. 📙 The VLDB Journal (2024).
• As part of a metalearning strategy for predicting market price movement 📙 Anais do Symposium on Knowledge Discovery, Mining and Learning (KDMiLe) (2023).
• Analyze US market price data. 📙 arXiv (2023).
• Capture meaningful properties of financial time series (performance is lower than using domain features). 📙 Working Papers REM.

General

• As a new algorithm fusing catch22 and the Matrix Profile, showing that the resulting the proposed C22MP is a state-of-the-art anomaly detector. 📙 2023 IEEE International Conference on Data Mining (ICDM) (2023).
• To compare performance on robust learning of noisy time-series collections. 📙 arXiv (2024).
• As part of an improved deep forest model for time-series classification. 📗 _ Neural Process Lett_ (2024).
• To understand dataset differences in evaluating foundation models for probabilistic time-series forecasting 📙 arXiv (2023).
• Predict performance of time-series forecasting algorithms. 📗 Expert Systems with Applications (2023)..
• Compare and cluster long time series 📗 IEEE International Conference on Knowledge Graph (ICKG) (2022).
• Cluster long time series. 📙 arXiv (2022).
• Track optimization trajectories for combinatorial optimization problems. 📙 arXiv (2022).
• Extend shapelets for time-series classification. 📗 Applied Sciences (2022).
• Perform meta-learning for time-series forecasting using 390 time-series features (including catch22). 📗 IEEE Access (2021).

Tutorials

• Using catch22 features in sktime.