# Publications using catch22 On this page, we keep track of scientific research publications that use *catch22*. Articles are labeled as follows: * πŸ“— = Journal is **open access**. * :closed\_book: = Journal is ***not***** open access**. * πŸ“™ = **Freely** accessible pre-print. * πŸ’» = **Code/Data available**. If you have used *catch22* in your published work, please **contact us by** [**email**](mailto:ben.d.fulcher@gmail.com) and we'll add it this growing list! *** ## πŸ–₯️ Algorithms *catch22* features have formed the basis of new algorithms:
Combine the Matrix Profile with catch22 features, as C22MP, yielding a state-of-the-art anomaly detector.
πŸ“• Knowl Inf Sys (2024).		/files/BE5NYxX0QAPDUOKgPm7Ghttps://doi.org/10.1007/s10115-024-02107-5

For developing semi-synthetic time series to understand algorithm performance.

πŸ“™ arXiv (2023).

/files/59hn2Tmo8m0QVoYX2juVhttps://arxiv.org/abs/2312.01344

A new method to reduce the complexity of feature-based explanations.

πŸ“— Information Fusion (2023).

/files/CxnBKdcLURaQEfGyBEUrhttps://www.sciencedirect.com/science/article/pii/S1566253523002713?via%3Dihub

The canonical interval time-series classifier.

πŸ“— IEEE International Conference on Big Data (2020).

/files/O091RUR4mE0UhhLZpmvohttps://doi.org/10.1109/BigData50022.2020.9378424
* "COCALITE: A Hybrid Model COmbining CAtch22 and LITE for Time Series Classification". :closed\_book:[*Badi et al. IEEE International Conference on Big Data* *(2024)*. ](https://ieeexplore.ieee.org/document/10825872) * A toolbox for predictive analytics (feature extraction and selection) demonstrated on wind turbine bearing condition classification, hydraulic systems condition monitoring, CNC tool wear estimation, and respiratory health monitoring. :closed\_book:[ *Zhou et al. Annual Symposium on Reliability and Maintainability (2025)*](https://doi.org/10.1109/RAMS48127.2025.10935234). *** ## Applications *catch22* features have been used in applications to: ### ⌚ Physiological and other sensors
Distinguish pain responses to hot and cold stimuli from electrodermal Activity and electromyography.
πŸ“™ Ozek et al., Research Square (2024).		/files/oNkelw4qxxlFYHcaPv1fhttps://www.researchsquare.com/article/rs-4469036/v1

Classify hyperkinetic, tonic, and tonic-clonic seizures using unsupervised clustering of video signals.

πŸ“— Frontiers in Neurology (2023).

/files/ydoJvVsEpXKAojgQMaKHhttps://www.frontiersin.org/journals/neurology/articles/10.3389/fneur.2023.1270482/full
Estimate pain intensity from physiological sensors.πŸ“™ arXiv (2023)./files/6KS2OXH4eGN9gUFpejSxhttps://arxiv.org/abs/2311.08569

Classify human exercises using wearable sensors and video data.

πŸ“• Joint European Conference on Machine Learning and Knowledge Discovery in Databases (2023).

/files/47X8XJO7shkgYJ94kRF4https://link.springer.com/chapter/10.1007/978-3-031-43427-3_19

Classify advertising engagement using affect and physiological signals of heart rate, electrodermal activity, pupil dilation, and skin temperature.

πŸ“— Sensors (2023).

/files/RxNWlKbCrhbdLi4iSgPehttps://www.mdpi.com/1424-8220/23/15/6916

Determine the type of breathing using wireless sensors with a motion capture system.

πŸ“— Algorithms (2023).

/files/KzWWoqrznqCetH5nFj9Whttps://www.mdpi.com/1999-4893/16/5/249

Automate general movements assessment for Cerebral Palsy from smartphone videos.

πŸ“—PLOS Digital Health (2024).

πŸ“™ medRxiv (2023).

πŸ’» Code.

/files/GD5PQ2jSnmHXkuS41wtNhttps://www.medrxiv.org/content/10.1101/2023.04.03.23288092v1

Detect stress levels in real time from multiple physiological signals (heart rate, blood pressure, electrodermal activity, and respiration).

πŸ“— IEEE Access (2023).

/files/CFUVpazzrLhViLV3tMhhhttps://ieeexplore.ieee.org/abstract/document/10063853

Comparison to ShapAAL method for sensor time-series classification.

πŸ“— PLOS ONE (2022).

/files/PtEdnAIhShvbYd57xLgthttps://journals.plos.org/plosone/article?id=10.1371/journal.pone.0277975

Extract markers of cardiometabolic disease risk from wearable device recordings.

πŸ“— Journal of Medical Internet Research (2022).

/files/jnToV0Pgxt7XZduKGXBhhttps://www.jmir.org/2022/7/e34669
Predict behavioural change from physiological signals. πŸ“— Sensors (2022)./files/Kd0zmzPu4iHuPz7RqARwhttps://www.mdpi.com/1424-8220/22/9/3468#

Estimate objective pain intensity using physiological sensors, paving the way for developing a wearable pain measurement device.

πŸ“— PLOS ONE (2021).

/files/hoaNgKK0mx9WxsX0J5H3https://journals.plos.org/plosone/article?id=10.1371/journal.pone.0254108
*** ### 🧬 Biology, physiology, neuroscience, pathology, and ecology
Predict pathological complete response in breast cancer from dynamic contrast-enhanced magnetic resonance images.
πŸ“— Breast Cancer Research (2024).		/files/q9rOTqTuzQxG3rWqhBIHhttps://breast-cancer-research.biomedcentral.com/articles/10.1186/s13058-024-01836-3

Predict species and age of malarial mosquitoes using mid-infrared spectroscopy.

πŸ“— Data Science Journal (2024).

/files/uu5LyRxj3IaIprwLTMXNhttps://doi.org/10.5334/dsj-2024-025

Classify calf behaviour from accelerometer signals.

πŸ“™ arXiv (2024).

/files/OOOfMw9F98JNZ3A9fXCXhttps://arxiv.org/abs/2404.18159

Detect early signals of disease outbreaks from incidence data.

πŸ“—PLOS Computational Biology (2025).

πŸ“™arXiv (2024).

/files/QPbHRTh0JtKsxoJuxJaMhttps://arxiv.org/abs/2404.08893

Predict the incidence trends of infectious diseases.

πŸ“— BMC Bioinformatics (2024).

/files/Zqk5I5JtSb5svL2QLNGhhttps://bmcbioinformatics.biomedcentral.com/articles/10.1186/s12859-023-05621-5

Distinguish chemical stimuli from C. elegans chemosensory system recordings.

πŸ“™ bioRxiv (2024).

/files/cjKxw5fwYkGGqtg4PlxThttps://www.biorxiv.org/content/10.1101/2024.01.14.575365v1

Predict when an individual patient can switch from IV to oral antibiotic treatment from routinely collected clinical parameters from over 10,000 ICU stays.

πŸ“— Nature Comms. (2024).

/files/FvPjjg21kBT1ZADvxOOXhttps://www.nature.com/articles/s41467-024-44740-2

Track Drosophila in real time for high-throughput behavioural phenotyping.

πŸ“— eLife (2023).

/files/hJ8eT5XyH3snWCB6gU4Chttps://elifesciences.org/articles/86695

Predict of cardiomyocytes differentiation outcome from oxygen consumption rate time series from human-induced pluripotent stem cells.

πŸ“• Biotechnology and Bioengineering (2023).

/files/rn2oTkorG2qbFAvn8h1Bhttps://analyticalsciencejournals.onlinelibrary.wiley.com/doi/10.1002/bit.28489

Detect dynamic electrical signatures of human breast cancer cells from voltage imaging.

πŸ“— Comms. Bio. (2022).

/files/Z27GwP22DLn2Kd2h8wAGhttps://www.nature.com/articles/s42003-022-04077-2

Screen for COVID-19 using holographic microscopy reconstructed red blood cells.

πŸ“— Biomedical Optics Express (2022).

/files/9ijUe9lACdJLZRulknTBhttps://opg.optica.org/boe/fulltext.cfm?uri=boe-13-10-5377&id=502632

Evaluate similarity of synthetically generated peripheral nerve signals.

πŸ“• 10th International IEEE/EMBS Conference on Neural Engineering (NER) (2021).

/files/6FqF5mznZ74kmVDfKc5lhttps://ieeexplore.ieee.org/abstract/document/9441284

Understand influences on the dynamics of tree motion.

πŸ“— Biogeosciences (2021).

/files/0UrcaAO7hZnanweRKEvdhttps://bg.copernicus.org/articles/18/4059/2021/

* To quantify neural coding from MEG time series. [πŸ“™ Maleki & Karimi-Rouzbahani. *bioRxiv* (2025)](https://www.biorxiv.org/content/10.1101/2025.04.30.651376). * To classify peptides from blockage current time series measured from a nanopore-based device. :closed\_book:[Hoßbach et al., *The Journal of Chemical Physics* (2025).](https://doi.org/10.1063/5.0250399) :orange\_book: [*arXiv (2024)*](https://arxiv.org/abs/2408.14275)*.* * As a baseline for classifying marmoset monkey calls from audio. :green\_book: [Interspeech 2024 satellite event (2024)](https://vihar-2024.vihar.org/assets/VIHAR_2024_proceedings.pdf).πŸ“™ [Sarkar et al. *arXiv* (2024).](https://arxiv.org/abs/2407.16417) * To identify methamphetamine users from EEG recordings. πŸ“— [Meynaghizadeh-Zargar et al., *Biogeosciences* (2024)](https://biomedrb.com/Article/brb-4041). *** ### 🏭 Industry, energy and chemistry

Detect edge flag faults in wind turbines.

πŸ“— Wind Energy Sci. Discuss. (2023).

/files/GCPuAcr47uj7AVQqpTsshttps://wes.copernicus.org/articles/9/181/2024/

Compare the influence of imputation strategies for classifying household devices from electricity usage.

πŸ“•2023 Tenth International Conference on Social Networks Analysis, Management and Security (SNAMS).

/files/04sSIFyL8eWGVakw6BoIhttps://doi.org/10.1109/SNAMS60348.2023.10375473

Detect chemical analytes from chemiresistive hardware sensor arrays.

πŸ“™ arXiv (2023).

/files/m9PGt6AMmmL3KfICXSevhttps://arxiv.org/abs/2312.09871

Detect fraud from smart meters.

πŸ“— Journal of Internet Services and Applications (2023).

/files/POOLRqaOYer4L84gPk3rhttps://www.researchgate.net/publication/376641713_Predictive_Fraud_Detection_An_Intelligent_Method_for_Internet_of_Smart_Grid_Things_Systems

Appliance detection from very low-frequency smart meter time series.

πŸ“•ACM International Conference on Future Energy Systems (2023).

πŸ“™ ResearchGate (2023).

/files/VFALu7ZIgufa76LcekRHhttps://www.researchgate.net/profile/Adrien-Petralia-2/publication/370654257_Appliance_Detection_Using_Very_Low-Frequency_Smart_Meter_Time_Series/links/645c0b48f43b8a29ba40dd25/Appliance-Detection-Using-Very-Low-Frequency-Smart-Meter-Time-Series.pdf

Track on-board diagnostics for monitoring engine operations.

πŸ“— Proceedings of the 8th International Conference on Vehicle Technology and Intelligent Transport Systems - VEHITS (2022).

/files/qvc8mDBsnffKr2kXbqtMhttps://doi.org/10.5220/0011036400003191

Detect anomalies in cloud services, where using catch22 resulted in the highest performance.

πŸ“— IoT (2022).

/files/oQekLFM805gvDw2ixusPhttps://www.mdpi.com/2624-831X/3/1/8

Predict anode effects in aluminium production at least 1 min of advance from TRIMET Aluminium SE Essen (TAE) time-series data.

πŸ“— Applied Sciences (2021).

/files/vslIOSM9ZyqWCONgSBpChttps://www.mdpi.com/2076-3417/10/24/9050
Classify vehicle trajectories from unmanned aerial vehicle-derived trajectories. πŸ“—Teo et al. ISPRS Int. J. Geo-Inf. (2024)./files/0Wm0nsvzxOpaCQLk1mUHhttps://www.mdpi.com/2220-9964/13/8/264
**Others**: * Audio classification. [πŸ“™ Marzano et al. (2025) *arXiv*](https://arxiv.org/abs/2503.17018). * Hard disk drive failure prediction. [πŸ“— Li et al. (2025) *Engineering Applications of Artificial Intelligence*.](https://doi.org/10.1016/j.engappai.2025.110674) * Predicting different types of induction motor failure. :closed\_book: [*Li et al., IEEE Annual Symposium on Reliability and Maintainability (2025).*](https://ieeexplore.ieee.org/document/10935284) * Analyzing appliance consumption by automatically detecting and classifying appliance activations in industrial kitchens. πŸ“— [*Martins et al. Computers and Electrical Engineering* (2025).](https://doi.org/10.1016/j.compeleceng.2025.110163) * Sound Analysis of Drop Characteristics by Evaluation of Impact on Water Pool. Arogeti et al. :closed\_book:[*IEEE 2024 Signal Processing: Algorithms, Architectures, Arrangements, and Applications (2024)*](https://doi.org/10.23919/SPA61993.2024.10715636)*.* *** ### 🧠 Neuroimaging

EEG classification using AutoML.

πŸ“™ Anais do Symposium on Knowledge Discovery, Mining and Learning (KDMiLe) (2023).

/files/pZdyb97cg0MLpQy3hQGahttps://repositorio.usp.br/directbitstream/0a2656f3-54e2-449d-ba1a-1db95ca007d3/3142491.pdf

Infer rules underlying experience of subjective liking of artwork stimuli from EEG.

πŸ“— PLOS ONE (2023).

/files/xyh8EsldJR5vfw1w5CdIhttps://doi.org/10.1371/journal.pone.0287513
*** * Classify Multiple Sclerosis from full-field visual evoked potentials. πŸ“— [Banijamali et al., *Doc Ophthalmol* (2024).](https://link.springer.com/article/10.1007/s10633-024-09980-z) * Investigate the neural correlates of dreaming. πŸ“— [Wong et al. PsyArXiv (2025).](https://osf.io/preprints/psyarxiv/69e43_v1) ### πŸ”­ Meteorology and astronomy

Generate long-term air temperature forecasts as part of explainable AI models.

πŸ“— Atmospheric Research (2023).

/files/YvklpxnfzLavjRWBtXkChttps://doi.org/10.1016/j.atmosres.2023.106608

Detect earthquakes.

πŸ“™ arXiv (2022).

/files/MdBruiJq1HLiCgHiwxq0https://doi.org/10.48550/arXiv.2205.00525

Classify exoplanets from light curves.

πŸ“™ Student dissertation (2019).

/files/Es2GOAvy5HSen2OcMDHwhttp://urn.kb.se/resolve?urn=urn:nbn:se:uu:diva-385690
* Predict solar flares from solar active region magnetic field data. [πŸ“™ *arXiv (2024)*](https://arxiv.org/abs/2410.00312)*.* *** ### πŸ›οΈ Finance and databases

As part of a meta-learning strategy for predicting market price movement.

πŸ“™ Anais do Symposium on Knowledge Discovery, Mining and Learning (KDMiLe) (2023).

/files/fckVDudjMzvgnJB4bYsfhttps://repositorio.usp.br/directbitstream/bd56a114-4b4c-49b7-a179-554e1d1fc099/3142482.pdf

Representations for time series in database management systems, such as Apache IoTDB, InfluxDB, OpenTSDB.

πŸ“™ The VLDB Journal (2024).

/files/BT83LiVVjkB3UhnFgD7Yhttps://link.springer.com/article/10.1007/s00778-024-00840-5

Analyze US market price data.

πŸ“™ arXiv (2023).

/files/7ki4NvnxIJbeDoz3j8Gthttps://arxiv.org/abs/2303.16117

Capture meaningful properties of financial time series (performance is lower than using domain features).

πŸ“™ Working Papers REM (2021).

/files/hhcYJjsaPkHVe0769i8nhttps://econpapers.repec.org/paper/iseremwps/wp01852021.htm

Distinguish texts generated by AI (LLMs) from text authored by humans.
πŸ“™Proceedings of the 19th Workshop on Innovative Use of NLP for Building Educational Applications (BEA 2024).		/files/wxXL23sDnlU8vrDia8zx
*** ### 🌍 General

To improve the efficiency and accuracy of time-series forecasting on target datasets using transfer learning.

πŸ“™ arXiv (2024).

/files/HdT8HisrUMh8PpzhDAAihttps://arxiv.org/abs/2404.06198

Compare and cluster long time series.

πŸ“— IEEE International Conference on Knowledge Graph (ICKG) (2022).

/files/41JZjt1sFIqsmCSa068Vhttps://doi.org/10.1109/ICKG55886.2022.00013

To understand dataset differences in evaluating foundation models for probabilistic time-series forecasting.

πŸ“™ arXiv (2023).

/files/sFDQ1jGR1QlxlL7WqGJxhttps://arxiv.org/abs/2310.08278

Predict performance of time-series forecasting algorithms.

πŸ“— Expert Systems with Applications (2023).

/files/3dGcdNsCk4TuM7ekGbbdhttps://linkinghub.elsevier.com/retrieve/pii/S0957417422020413

Track optimization trajectories for combinatorial optimization problems.

πŸ“™ arXiv (2022).

/files/zujPyT2xsjEvhSWrPl5Whttps://arxiv.org/abs/2211.15368

Extend shapelets for time-series classification.

πŸ“— Applied Sciences (2022).

/files/wNX5QCUYnGaxg9Tw7EjGhttps://www.mdpi.com/2076-3417/12/17/8685

Perform meta-learning for time-series forecasting.

πŸ“— IEEE Access (2021).

/files/O62ZEK2ofIdpA9WCPjPPhttps://ieeexplore.ieee.org/document/9410467
Evaluate time-series imputation methods.
πŸ“—Proc. VLDB Endowment (2024).
/files/WjjJyIb7bMxeFnCSZTsBhttps://www.researchgate.net/publication/383497799_ImputeVIS_An_Interactive_Evaluator_to_Benchmark_Imputation_Techniques_for_Time_Series_Data
*** ## Tutorials
Using catch22 features in sktime./files/K7R92zDtgtTXnGcR8Zhnhttps://www.sktime.net/en/stable/examples/transformation/catch22.html
*** --- # Agent Instructions: Querying This Documentation If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question. Perform an HTTP GET request on the current page URL with the `ask` query parameter: ``` GET https://time-series-features.gitbook.io/catch22/welcome-to-catch22/publications-using-catch22.md?ask= ``` The question should be specific, self-contained, and written in natural language. The response will contain a direct answer to the question and relevant excerpts and sources from the documentation. Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.