{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,24]],"date-time":"2026-06-24T10:37:25Z","timestamp":1782297445831,"version":"3.54.5"},"reference-count":52,"publisher":"MDPI AG","issue":"19","license":[{"start":{"date-parts":[[2022,9,27]],"date-time":"2022-09-27T00:00:00Z","timestamp":1664236800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100000780","name":"European Research Council Proof of Concept grant NeuroSoNew","doi-asserted-by":"publisher","award":["842243"],"award-info":[{"award-number":["842243"]}],"id":[{"id":"10.13039\/501100000780","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>Electroencephalogram (EEG) data are typically affected by artifacts. The detection and removal of bad channels (i.e., with poor signal-to-noise ratio) is a crucial initial step. EEG data acquired from different populations require different cleaning strategies due to the inherent differences in the data quality, the artifacts\u2019 nature, and the employed experimental paradigm. To deal with such differences, we propose a robust EEG bad channel detection method based on the Local Outlier Factor (LOF) algorithm. Unlike most existing bad channel detection algorithms that look for the global distribution of channels, LOF identifies bad channels relative to the local cluster of channels, which makes it adaptable to any kind of EEG. To test the performance and versatility of the proposed algorithm, we validated it on EEG acquired from three populations (newborns, infants, and adults) and using two experimental paradigms (event-related and frequency-tagging). We found that LOF can be applied to all kinds of EEG data after calibrating its main hyperparameter: the LOF threshold. We benchmarked the performance of our approach with the existing state-of-the-art (SoA) bad channel detection methods. We found that LOF outperforms all of them by improving the F1 Score, our chosen performance metric, by about 40% for newborns and infants and 87.5% for adults.<\/jats:p>","DOI":"10.3390\/s22197314","type":"journal-article","created":{"date-parts":[[2022,9,28]],"date-time":"2022-09-28T03:30:37Z","timestamp":1664335837000},"page":"7314","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":33,"title":["Adaptable and Robust EEG Bad Channel Detection Using Local Outlier Factor (LOF)"],"prefix":"10.3390","volume":"22","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9286-4687","authenticated-orcid":false,"given":"Velu Prabhakar","family":"Kumaravel","sequence":"first","affiliation":[{"name":"Digital Society Center, Fondazione Bruno Kessler, 38123 Trento, Italy"},{"name":"Center for Mind\/Brain Sciences, University of Trento, 38068 Rovereto, Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2362-7853","authenticated-orcid":false,"given":"Marco","family":"Buiatti","sequence":"additional","affiliation":[{"name":"Center for Mind\/Brain Sciences, University of Trento, 38068 Rovereto, Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4836-6370","authenticated-orcid":false,"given":"Eugenio","family":"Parise","sequence":"additional","affiliation":[{"name":"Center for Mind\/Brain Sciences, University of Trento, 38068 Rovereto, Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9047-9868","authenticated-orcid":false,"given":"Elisabetta","family":"Farella","sequence":"additional","affiliation":[{"name":"Digital Society Center, Fondazione Bruno Kessler, 38123 Trento, Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2022,9,27]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"268","DOI":"10.1016\/j.mayocp.2011.12.008","article-title":"Brain-Computer Interfaces in Medicine","volume":"87","author":"Shih","year":"2012","journal-title":"Mayo Clin. Proc."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"giz002","DOI":"10.1093\/gigascience\/giz002","article-title":"EEG dataset and OpenBMI toolbox for three BCI paradigms: An investigation into BCI illiteracy","volume":"8","author":"Lee","year":"2019","journal-title":"GigaScience"},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"407","DOI":"10.1016\/j.bspc.2016.09.005","article-title":"Trends in EEG-BCI for daily-life: Requirements for artifact removal","volume":"31","author":"Minguillon","year":"2017","journal-title":"Biomed. Signal Process. Control"},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Jiang, X., Bian, G.B., and Tian, Z. (2019). Removal of Artifacts from EEG Signals: A Review. Sensors, 19.","DOI":"10.3390\/s19050987"},{"key":"ref_5","unstructured":"Touretzky, D., Mozer, M., and Hasselmo, M. (1995). Independent Component Analysis of Electroencephalographic Data. Advances in Neural Information Processing Systems, MIT Press."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"30","DOI":"10.1186\/1744-9081-7-30","article-title":"Automatic classification of artifactual ICA-components for artifact removal in EEG signals","volume":"7","author":"Winkler","year":"2011","journal-title":"Behav. Brain Funct."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"229","DOI":"10.1111\/j.1469-8986.2010.01061.x","article-title":"ADJUST: An automatic EEG artifact detector based on the joint use of spatial and temporal features","volume":"48","author":"Mognon","year":"2011","journal-title":"Psychophysiology"},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"181","DOI":"10.1016\/j.neuroimage.2019.05.026","article-title":"ICLabel: An automated electroencephalographic independent component classifier, dataset, and website","volume":"198","author":"Makeig","year":"2019","journal-title":"NeuroImage"},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"e13566","DOI":"10.1111\/psyp.13566","article-title":"Adjusting ADJUST: Optimizing the ADJUST algorithm for pediatric data using geodesic nets","volume":"57","author":"Leach","year":"2020","journal-title":"Psychophysiology"},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"2553","DOI":"10.1109\/TBME.2015.2481482","article-title":"Real-time neuroimaging and cognitive monitoring using wearable dry EEG","volume":"62","author":"Mullen","year":"2015","journal-title":"IEEE Trans. Biomed. Eng."},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Blum, S., Mirkovic, B., and Debener, S. (2019, January 6\u20139). Evaluation of Riemannian ASR on cEEGrid data: An artifact correction method for BCIs. Proceedings of the 2019 IEEE International Conference on Systems, Man and Cybernetics (SMC), Bari, Italy.","DOI":"10.1109\/SMC.2019.8914319"},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Kumaravel, V.P., Kartsch, V., Benatti, S., Vallortigara, G., Farella, E., and Buiatti, M. (November, January 31). Efficient Artifact Removal from Low-Density Wearable EEG using Artifacts Subspace Reconstruction. Proceedings of the 2021 43rd Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC), Jalisco, Mexico.","DOI":"10.1109\/EMBC46164.2021.9629771"},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"101068","DOI":"10.1016\/j.dcn.2022.101068","article-title":"NEAR: An artifact removal pipeline for human newborn EEG data","volume":"54","author":"Kumaravel","year":"2022","journal-title":"Dev. Cogn. Neurosci."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"4625","DOI":"10.1073\/pnas.1812419116","article-title":"Cortical route for facelike pattern processing in human newborns","volume":"116","author":"Buiatti","year":"2019","journal-title":"Proc. Natl. Acad. Sci. USA"},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"427","DOI":"10.1145\/335191.335437","article-title":"Efficient Algorithms for Mining Outliers from Large Data Sets","volume":"29","author":"Ramaswamy","year":"2000","journal-title":"SIGMOD Rec."},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Goldstein, M., and Uchida, S. (2016). A Comparative Evaluation of Unsupervised Anomaly Detection Algorithms for Multivariate Data. PLoS ONE, 11.","DOI":"10.1371\/journal.pone.0152173"},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"93","DOI":"10.1145\/335191.335388","article-title":"LOF: Identifying Density-Based Local Outliers","volume":"29","author":"Breunig","year":"2000","journal-title":"SIGMOD Rec."},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Kriegel, H.P., Kr\u00f6ger, P., Schubert, E., and Zimek, A. (2009, January 2\u20136). LoOP: Local Outlier Probabilities. Proceedings of the 18th ACM Conference on Information and Knowledge Management (CIKM\u201909), Hong Kong, China.","DOI":"10.1145\/1645953.1646195"},{"key":"ref_19","unstructured":"Hofmann, M., and Klinkenberg, R. (2013). RapidMiner: Data Mining Use Cases and Business Analytics Applications, Chapman & Hall\/CRC."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"48","DOI":"10.1016\/j.probengmech.2012.06.002","article-title":"A novel probabilistic method for robust parametric identification and outlier detection","volume":"30","author":"Yuen","year":"2012","journal-title":"Probabilistic Eng. Mech."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"632","DOI":"10.1016\/j.cma.2016.10.004","article-title":"Outlier detection and robust regression for correlated data","volume":"313","author":"Yuen","year":"2017","journal-title":"Comput. Methods Appl. Mech. Eng."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"9","DOI":"10.1016\/j.jneumeth.2003.10.009","article-title":"EEGLAB: An open source toolbox for analysis of single-trial EEG dynamics including independent component analysis","volume":"134","author":"Delorme","year":"2004","journal-title":"J. Neurosci. Methods"},{"key":"ref_23","first-page":"16","article-title":"The PREP pipeline: Standardized preprocessing for large-scale EEG analysis","volume":"9","author":"Mullen","year":"2015","journal-title":"Front. Neuroinform."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"152","DOI":"10.1016\/j.jneumeth.2010.07.015","article-title":"Fully Automated Statistical Thresholding for EEG artifact Rejection","volume":"192","author":"Nolan","year":"2010","journal-title":"J. Neurosci. Methods"},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"97","DOI":"10.3389\/fnins.2018.00097","article-title":"The Harvard Automated Processing Pipeline for Electroencephalography (HAPPE): Standardized Processing Software for Developmental and High-Artifact Data","volume":"12","author":"Wilkinson","year":"2018","journal-title":"Front. Neurosci."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"224","DOI":"10.1016\/0010-468X(78)90029-6","article-title":"On the stationarity and normality of the electroencephalographic data during sleep stages","volume":"8","author":"Sugimoto","year":"1978","journal-title":"Comput. Programs Biomed."},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"056057","DOI":"10.1088\/1741-2552\/ac2bf8","article-title":"EEGdenoiseNet: A benchmark dataset for deep learning solutions of EEG denoising","volume":"18","author":"Zhang","year":"2021","journal-title":"J. Neural Eng."},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"Paissan, F., Kumaravel, V., and Farella, E. (2022, January 1\u20133). Interpretable CNN for Single-Channel Artifacts Detection in Raw EEG Signals. Proceedings of the 2022 IEEE Sensors Applications Symposium (SAS), Sundsvall, Sweden.","DOI":"10.1109\/SAS54819.2022.9881381"},{"key":"ref_29","doi-asserted-by":"crossref","unstructured":"Ho, T.K.K., and Armanfard, N. (2022). Self-Supervised Learning for Anomalous Channel Detection in EEG Graphs: Application to Seizure Analysis. arXiv.","DOI":"10.1609\/aaai.v37i7.25952"},{"key":"ref_30","doi-asserted-by":"crossref","unstructured":"Han, J., Kamber, M., and Pei, J. (2012). 12\u2014Outlier Detection. Data Mining, Morgan Kaufmann. [3rd ed.]. The Morgan Kaufmann Series in Data Management Systems.","DOI":"10.1016\/B978-0-12-381479-1.00012-5"},{"key":"ref_31","doi-asserted-by":"crossref","unstructured":"Fix, E., and Hodges, J. (1951). Discriminatory Analysis, Nonparametric Discrimination: Consistency Properties, Randolph Field. USAF School of Aviation Medicine.","DOI":"10.1037\/e471672008-001"},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"13","DOI":"10.1016\/j.jneumeth.2018.08.001","article-title":"SEREEGA: Simulating event-related EEG activity","volume":"309","author":"Krol","year":"2018","journal-title":"J. Neurosci. Methods"},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"728","DOI":"10.1177\/0956797612438734","article-title":"Electrophysiological Evidence for the Understanding of Maternal Speech by 9-Month-Old Infants","volume":"23","author":"Parise","year":"2012","journal-title":"Psychol. Sci."},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"48","DOI":"10.1007\/s10548-019-00725-9","article-title":"Real-time EEG feedback on alpha power lateralization leads to behavioral improvements in a covert attention task","volume":"33","author":"Schneider","year":"2020","journal-title":"Brain Topogr."},{"key":"ref_35","unstructured":"(2022, February 25). FASTER Bad Channel Function. Available online: https:\/\/github.com\/mortonne\/...\/eeglab\/faster\/channel_properties.m."},{"key":"ref_36","unstructured":"(2022, February 25). EEGLAB Plugin: Clean_rawdata. Available online: https:\/\/github.com\/sccn\/clean_rawdata."},{"key":"ref_37","doi-asserted-by":"crossref","unstructured":"Dalianis, H. (2018). Evaluation Metrics and Evaluation. Clinical Text Mining, Springer International Publishing.","DOI":"10.1007\/978-3-319-78503-5_6"},{"key":"ref_38","unstructured":"(2022, February 25). EEGLAB Plugin: NEAR. Available online: https:\/\/github.com\/vpKumaravel\/NEAR."},{"key":"ref_39","doi-asserted-by":"crossref","first-page":"30","DOI":"10.1016\/j.patrec.2016.05.007","article-title":"Natural neighbor: A self-adaptive neighborhood method without parameter K","volume":"80","author":"Zhu","year":"2016","journal-title":"Pattern Recognit. Lett."},{"key":"ref_40","unstructured":"MATLAB (2018). Version 7.10.0 (R2018b), The MathWorks Inc."},{"key":"ref_41","first-page":"2825","article-title":"Scikit-learn: Machine Learning in Python","volume":"12","author":"Pedregosa","year":"2011","journal-title":"J. Mach. Learn. Res."},{"key":"ref_42","doi-asserted-by":"crossref","unstructured":"Kuhn, M., and Johnson, K. (2013). Applied Predictive Modeling, Springer. [1st ed.].","DOI":"10.1007\/978-1-4614-6849-3"},{"key":"ref_43","doi-asserted-by":"crossref","unstructured":"James, G., Witten, D., Hastie, T., and Tibshirani, R. (2013). An Introduction to Statistical Learning: With Applications in R, Springer.","DOI":"10.1007\/978-1-4614-7138-7"},{"key":"ref_44","doi-asserted-by":"crossref","first-page":"158","DOI":"10.1109\/JBHI.2014.2333010","article-title":"Unsupervised Eye Blink Artifact Denoising of EEG Data with Modified Multiscale Sample Entropy, Kurtosis, and Wavelet-ICA","volume":"19","author":"Mahajan","year":"2015","journal-title":"IEEE J. Biomed. Health Inform."},{"key":"ref_45","first-page":"240","article-title":"Kurtosis, Renyi\u2019s entropy and independent component scalp maps for the automatic artifact rejection from EEG data","volume":"2","author":"Greco","year":"2006","journal-title":"Int. J. Signal Process."},{"key":"ref_46","doi-asserted-by":"crossref","first-page":"1443","DOI":"10.1016\/j.neuroimage.2006.11.004","article-title":"Enhanced detection of artifacts in EEG data using higher-order statistics and independent component analysis","volume":"34","author":"Delorme","year":"2007","journal-title":"NeuroImage"},{"key":"ref_47","doi-asserted-by":"crossref","unstructured":"Bian, N.Y., Wang, B., Cao, Y., and Zhang, L. (2006). Automatic Removal of Artifacts from EEG Data Using ICA and Exponential Analysis. Advances in Neural Networks\u2014ISNN 2006, Springer.","DOI":"10.1007\/11760023_106"},{"key":"ref_48","doi-asserted-by":"crossref","first-page":"293","DOI":"10.1007\/s00422-001-0298-6","article-title":"Blind noise reduction for multisensory signals using ICA and subspace filtering, with application to EEG analysis","volume":"86","author":"Vorobyov","year":"2002","journal-title":"Biol. Cybern."},{"key":"ref_49","doi-asserted-by":"crossref","first-page":"638","DOI":"10.1093\/cercor\/bhs047","article-title":"Early Development of Spatial Patterns of Power-Law Frequency Scaling in fMRI Resting-State and EEG Data in the Newborn Brain","volume":"23","author":"Fransson","year":"2012","journal-title":"Cereb. Cortex"},{"key":"ref_50","unstructured":"(2022, February 25). EEGLAB Plugin: TrimOutlier. Available online: https:\/\/github.com\/sccn\/trimOutlier."},{"key":"ref_51","doi-asserted-by":"crossref","first-page":"48","DOI":"10.1007\/s10548-019-00725-9","article-title":"Real-time EEG Feedback on Alpha Power Lateralization Leads to Behavioral Improvements in a Covert Attention Task","volume":"33","author":"Schneider","year":"2019","journal-title":"Brain Topogr."},{"key":"ref_52","first-page":"8406","article-title":"EEG Normal Waveforms","volume":"54","author":"Nayak","year":"2022","journal-title":"StatPearls"}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/22\/19\/7314\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T00:40:12Z","timestamp":1760143212000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/22\/19\/7314"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,9,27]]},"references-count":52,"journal-issue":{"issue":"19","published-online":{"date-parts":[[2022,10]]}},"alternative-id":["s22197314"],"URL":"https:\/\/doi.org\/10.3390\/s22197314","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,9,27]]}}}