{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,17]],"date-time":"2026-07-17T15:46:00Z","timestamp":1784303160930,"version":"3.55.0"},"reference-count":33,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2025,11,1]],"date-time":"2025-11-01T00:00:00Z","timestamp":1761955200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/deed.de"},{"start":{"date-parts":[[2025,11,20]],"date-time":"2025-11-20T00:00:00Z","timestamp":1763596800000},"content-version":"vor","delay-in-days":19,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/deed.de"}],"funder":[{"DOI":"10.13039\/501100005626","name":"Universit\u00e4t Regensburg","doi-asserted-by":"crossref","id":[{"id":"10.13039\/501100005626","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Datenbank Spektrum"],"published-print":{"date-parts":[[2025,11]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>Eye-Tracking data provides valuable insights into human behavior, yet its high variability to noise require robust preprocessing to ensure meaningful analysis. This study introduces and evaluates a\u00a0systematic preprocessing pipeline tailored to enhance machine learning classifier performance in the context of Eye-Tracking data, on a\u00a0dataset on academic cheating detection. Unlike prior work focusing on isolated preprocessing steps, our approach explores 193 configurations by combining techniques for missing value imputation, outlier handling, normalization, smoothing, feature limiting, and filtering. A\u00a0Random Forest classifier is used consistently across all configurations due to its robustness and prior success in similar domains. Our results demonstrate that well-designed preprocessing pipelines can substantially improve classification accuracy. Additionally, a\u00a0feature importance analysis reveals that static spatial and camera-based metrics outperform traditional gaze dynamics in predictive power. This research aims to create a\u00a0reusable framework for Eye-Tracking data.<\/jats:p>","DOI":"10.1007\/s13222-025-00518-4","type":"journal-article","created":{"date-parts":[[2025,11,20]],"date-time":"2025-11-20T19:52:50Z","timestamp":1763668370000},"page":"153-166","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Impact of Preprocessing on Classification Results of Eye-Tracking-Data","Einfluss von Preprocessing auf die Klassifikationsgenauigkeit von Eye-Tracking Daten"],"prefix":"10.1007","volume":"25","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-1914-598X","authenticated-orcid":false,"given":"Jennifer","family":"Landes","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Meike","family":"Klettke","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sonja","family":"K\u00f6ppl","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,11,20]]},"reference":[{"key":"518_CR1","doi-asserted-by":"publisher","first-page":"299","DOI":"10.1145\/2818346.2820742","volume-title":"Proceedings of the 2015 ACM on International Conference on Multimodal Interaction","author":"R Bixler","year":"2015","unstructured":"Bixler\u00a0R, Blanchard\u00a0N, Garrison\u00a0L, D\u2019Mello\u00a0S (2015) Automatic Detection of Mind Wandering During Reading Using Gaze and Physiology. In: Proceedings of the 2015 ACM on International Conference on Multimodal Interaction. ACM, Seattle, Washington, pp\u00a0299\u2013306 https:\/\/doi.org\/10.1145\/2818346.2820742"},{"key":"518_CR2","series-title":"CEUR Workshop Proceedings","first-page":"35","volume-title":"Proceedings of the 35th GI-Workshop Grundlagen Von Datenbanken","author":"J Landes","year":"2024","unstructured":"Landes\u00a0J, K\u00f6ppl\u00a0S, Klettke\u00a0M (2024) Data processing pipeline for eye-tracking analysis. In: Proceedings of the 35th GI-Workshop Grundlagen Von Datenbanken Herdecke, May 22\u201324, 2024. CEUR Workshop Proceedings, vol 3710, pp\u00a035\u201342 (https:\/\/ceur-ws.org\/Vol-3710\/paper6.pdf Accessed 2025-04-10. CEUR-WS.org)"},{"key":"518_CR3","doi-asserted-by":"publisher","first-page":"100055","DOI":"10.1016\/j.caeo.2021.100055","volume":"2","author":"S Janke","year":"2021","unstructured":"Janke\u00a0S, Rudert\u00a0SC, Petersen\u00a0FTM, Daumiller\u00a0M (2021) Cheating in the wake of COVID-19: how dangerous is ad-hoc online testing for academic integrity? Comput Educ Open 2:100055. https:\/\/doi.org\/10.1016\/j.caeo.2021.100055","journal-title":"Comput Educ Open"},{"key":"518_CR4","series-title":"LNI","doi-asserted-by":"publisher","first-page":"1449","DOI":"10.18420\/INF2024_126","volume-title":"54. Jahrestagung der Gesellschaft F\u00fcr Informatik, INFORMATIK 2024\u2014Lock in or Log Out? Wie Digitale Souver\u00e4nit\u00e4t Gelingt","author":"J Landes","year":"2024","unstructured":"Landes\u00a0J, K\u00f6ppl\u00a0S, Klettke\u00a0M (2024) Comparison of Classifiers for Eye-Tracking Data. In: 54. Jahrestagung der Gesellschaft F\u00fcr Informatik, INFORMATIK 2024\u2014Lock in or Log Out? Wie Digitale Souver\u00e4nit\u00e4t Gelingt Wiesbaden, September 24\u201326, 2024. LNI, vol P\u2011352. Gesellschaft f\u00fcr Informatik, Bonn, pp\u00a01449\u20131462 https:\/\/doi.org\/10.18420\/INF2024_126"},{"key":"518_CR5","series-title":"Lecture Notes in Informatics (LNI)","doi-asserted-by":"publisher","first-page":"235","DOI":"10.18420\/BTW2025-127","volume-title":"BTW2025 \u2013 Datenbanksysteme F\u00fcr Business, Technologie und Web \u2013 Workshopband","author":"J Landes","year":"2025","unstructured":"Landes\u00a0J, Klettke\u00a0M, K\u00f6ppl\u00a0S (2025) Impact of preprocessing on classification results of eye-tracking-data. In: BTW2025 \u2013 Datenbanksysteme F\u00fcr Business, Technologie und Web \u2013 Workshopband. Lecture Notes in Informatics (LNI), vol P\u2011363. Gesellschaft f\u00fcr Informatik e. V., pp\u00a0235\u2013256 https:\/\/doi.org\/10.18420\/BTW2025-127 (Refereed conference paper)"},{"key":"518_CR6","volume-title":"The application of machine learning techniques to time-series data","author":"RS Mitchell","year":"1995","unstructured":"Mitchell\u00a0RS (1995) The application of machine learning techniques to time-series data. University of Waikato, Department of Computer Science"},{"key":"518_CR7","doi-asserted-by":"publisher","DOI":"10.3389\/fbioe.2020.00260","author":"J Burdack","year":"2020","unstructured":"Burdack\u00a0J, Horst\u00a0F, Giesselbach\u00a0S, Hassan\u00a0I, Daffner\u00a0S, Sch\u00f6llhorn\u00a0WI (2020) Systematic comparison of the influence of different data preprocessing methods on the performance of gait classifications using machine learning. Front Bioeng Biotechnol. https:\/\/doi.org\/10.3389\/fbioe.2020.00260","journal-title":"Front Bioeng Biotechnol"},{"issue":"1","key":"518_CR8","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s10115-011-0463-8","volume":"33","author":"F Kamiran","year":"2012","unstructured":"Kamiran\u00a0F, Calders\u00a0T (2012) Data preprocessing techniques for classification without discrimination. Knowl Inf Syst 33(1):1\u201333. https:\/\/doi.org\/10.1007\/s10115-011-0463-8","journal-title":"Knowl Inf Syst"},{"key":"518_CR9","unstructured":"Olsson P (2007) Real-time and offline filters for eye tracking. https:\/\/urn.kb.se\/resolve?urn=urn:nbn:se:kth:diva-106244. Accessed 2024-12-10"},{"key":"518_CR10","doi-asserted-by":"publisher","DOI":"10.1002\/9780470575758","volume-title":"Adaptive signal processing: next generation solutions","author":"T Adali","year":"2010","unstructured":"Adali\u00a0T, Haykin\u00a0S (2010) Adaptive signal processing: next generation solutions. Wiley, Hoboken"},{"key":"518_CR11","doi-asserted-by":"publisher","unstructured":"Li Y, Deng J, Wu Q, Wang Y (2021) Eye-tracking signals based affective classification employing deep gradient convolutional neural networks. https:\/\/doi.org\/10.9781\/ijimai.2021.06.002","DOI":"10.9781\/ijimai.2021.06.002"},{"issue":"3","key":"518_CR12","doi-asserted-by":"publisher","first-page":"1336","DOI":"10.3758\/s13428-018-1075-y","volume":"51","author":"ME Kret","year":"2019","unstructured":"Kret\u00a0ME, Sjak-Shie\u00a0EE (2019) Preprocessing pupil size data: Guidelines and code. Behav Res 51(3):1336\u20131342. https:\/\/doi.org\/10.3758\/s13428-018-1075-y","journal-title":"Behav Res"},{"key":"518_CR13","doi-asserted-by":"publisher","DOI":"10.3389\/fnins.2021.664490","author":"L-M Vortmann","year":"2021","unstructured":"Vortmann\u00a0L\u2011M, Knychalla\u00a0J, Annerer-Walcher\u00a0S, Benedek\u00a0M, Putze\u00a0F (2021) Imaging time series of eye tracking data to classify attentional states. Front Neurosci. https:\/\/doi.org\/10.3389\/fnins.2021.664490","journal-title":"Front Neurosci"},{"issue":"7","key":"518_CR14","doi-asserted-by":"publisher","first-page":"2146","DOI":"10.3390\/s18072146","volume":"18","author":"X Zheng","year":"2018","unstructured":"Zheng\u00a0X, Wang\u00a0M, Ordieres-Mer\u00e9\u00a0J (2018) Comparison of data preprocessing approaches for applying deep learning to human activity recognition in the context of industry 4.0. Sensors 18(7):2146. https:\/\/doi.org\/10.3390\/s18072146","journal-title":"Sensors"},{"key":"518_CR15","doi-asserted-by":"publisher","first-page":"116045","DOI":"10.1016\/j.trac.2020.116045","volume":"132","author":"P Mishra","year":"2020","unstructured":"Mishra\u00a0P, Biancolillo\u00a0A, Roger\u00a0JM, Marini\u00a0F, Rutledge\u00a0DN (2020) New data preprocessing trends based on ensemble of multiple preprocessing techniques. Trends Anal Chem 132:116045. https:\/\/doi.org\/10.1016\/j.trac.2020.116045","journal-title":"Trends Anal Chem"},{"key":"518_CR16","doi-asserted-by":"publisher","first-page":"218","DOI":"10.17221\/113\/2015-SWR","volume":"10","author":"A Gholizadeh","year":"2015","unstructured":"Gholizadeh\u00a0A, Boruvka\u00a0L, Saberioon\u00a0M, Koz\u00e1k\u00a0J, Va\u0161\u00e1t\u00a0R, Nemecek\u00a0K (2015) Comparing different data preprocessing methods for monitoring soil heavy metals based on soil spectral features. Soil Water Res 10:218\u2013227. https:\/\/doi.org\/10.17221\/113\/2015-SWR","journal-title":"Soil Water Res"},{"issue":"6","key":"518_CR17","doi-asserted-by":"publisher","first-page":"3308","DOI":"10.3390\/app15063308","volume":"15","author":"J Arnold","year":"2025","unstructured":"Arnold\u00a0J, Jost\u00a0F, Schneider\u00a0M, Schwarz\u00a0F, K\u00fcbler\u00a0TC (2025) A\u00a0systematic literature review of eye-tracking and machine learning methods for improving productivity and reading abilities. Appl Sci 15(6):3308. https:\/\/doi.org\/10.3390\/app15063308","journal-title":"Appl Sci"},{"key":"518_CR18","doi-asserted-by":"publisher","first-page":"796895","DOI":"10.3389\/fnbot.2021.796895","volume":"15","author":"J Lim","year":"2021","unstructured":"Lim\u00a0J, Mountstephens\u00a0J, Teo\u00a0J (2021) Eye-tracking feature extraction for biometric machine learning. Front Neurorobot 15:796895","journal-title":"Front Neurorobot"},{"issue":"24","key":"518_CR19","doi-asserted-by":"publisher","first-page":"8205","DOI":"10.3390\/s21248205","volume":"21","author":"L-M Vortmann","year":"2021","unstructured":"Vortmann\u00a0L\u2011M, Putze\u00a0F (2021) Combining implicit and explicit feature extraction for eye tracking. Sensors 21(24):8205","journal-title":"Sensors"},{"key":"518_CR20","unstructured":"Tawakuli A (2024) Time-series data preprocessing: a\u00a0survey and an evaluation. J\u00a0Time Ser Data Sci"},{"issue":"8","key":"518_CR21","doi-asserted-by":"publisher","first-page":"332","DOI":"10.3390\/a17080332","volume":"17","author":"M Usmani","year":"2024","unstructured":"Usmani\u00a0M et\u00a0al (2024) Preptimize: automation of time series data preprocessing framework. Algorithms 17(8):332","journal-title":"Algorithms"},{"key":"518_CR22","doi-asserted-by":"publisher","first-page":"63","DOI":"10.1016\/j.future.2021.09.033","volume":"128","author":"Y Zhang","year":"2022","unstructured":"Zhang\u00a0Y, Thorburn\u00a0PJ (2022) Handling missing data in near real-time environmental monitoring: a\u00a0system and a\u00a0review of selected methods. Future Gener Comput Syst 128:63\u201372. https:\/\/doi.org\/10.1016\/j.future.2021.09.033","journal-title":"Future Gener Comput Syst"},{"issue":"1","key":"518_CR23","doi-asserted-by":"publisher","first-page":"129","DOI":"10.1186\/s40537-021-00518-7","volume":"8","author":"H Nugroho","year":"2021","unstructured":"Nugroho\u00a0H, Utama\u00a0NP, Surendro\u00a0K (2021) Normalization and outlier removal in class center-based firefly algorithm for missing value imputation. J\u00a0Big Data 8(1):129. https:\/\/doi.org\/10.1186\/s40537-021-00518-7","journal-title":"J Big Data"},{"key":"518_CR24","doi-asserted-by":"publisher","first-page":"511","DOI":"10.1007\/978-981-10-7563-6_53","volume-title":"Information and Decision Sciences","author":"HP Vinutha","year":"2018","unstructured":"Vinutha\u00a0HP, Poornima\u00a0B, Sagar\u00a0BM (2018) Detection of outliers using Interquartile range technique from intrusion dataset. In: Information and Decision Sciences. Springer, Singapore, pp\u00a0511\u2013518 https:\/\/doi.org\/10.1007\/978-981-10-7563-6_53"},{"issue":"11","key":"518_CR25","doi-asserted-by":"publisher","first-page":"194","DOI":"10.3390\/fi12110194","volume":"12","author":"IM Pires","year":"2020","unstructured":"Pires\u00a0IM, Hussain\u00a0F, Garcia\u00a0N, Lameski\u00a0P, Zdravevski\u00a0E (2020) Homogeneous data normalization and deep learning: a\u00a0case study in human activity classification. Future Internet 12(11):194\u20131905. https:\/\/doi.org\/10.3390\/fi12110194","journal-title":"Future Internet"},{"issue":"1","key":"518_CR26","doi-asserted-by":"publisher","first-page":"020110","DOI":"10.1063\/5.0182879","volume":"2926","author":"ZS Priyambudi","year":"2024","unstructured":"Priyambudi\u00a0ZS, Nugroho\u00a0YS (2024) Which algorithm is better? An implementation of normalization to predict student performance. AIP Conf Proc 2926(1):20110. https:\/\/doi.org\/10.1063\/5.0182879","journal-title":"AIP Conf Proc"},{"key":"518_CR27","doi-asserted-by":"publisher","unstructured":"Patro SGK, Sahu KK (2015) Normalization: a\u00a0preprocessing stage. https:\/\/doi.org\/10.48550\/arXiv.1503.06462","DOI":"10.48550\/arXiv.1503.06462"},{"key":"518_CR28","doi-asserted-by":"publisher","DOI":"10.16910\/jemr.14.3.6","author":"MH Raju","year":"2023","unstructured":"Raju\u00a0MH, Friedman\u00a0L, Bouman\u00a0TM, Komogortsev\u00a0OV (2023) Filtering eye-tracking data from an eyelink 1000: comparing heuristic, Savitzky-Golay, IIR and FIR digital filters. J\u00a0Eye Mov Res. https:\/\/doi.org\/10.16910\/jemr.14.3.6","journal-title":"J Eye Mov Res"},{"issue":"3","key":"518_CR29","doi-asserted-by":"publisher","first-page":"971","DOI":"10.15157\/IJITIS.2022.5.3.971-1005","volume":"5","author":"LO Joel","year":"2022","unstructured":"Joel\u00a0LO, Doorsamy\u00a0W, Paul\u00a0BS (2022) A\u00a0review of missing data handling techniques for machine learning. Int J Innov Technol Interdiscip Sci 5(3):971\u20131005. https:\/\/doi.org\/10.15157\/IJITIS.2022.5.3.971-1005","journal-title":"Int J Innov Technol Interdiscip Sci"},{"key":"518_CR30","first-page":"2825","volume":"12","author":"F Pedregosa","year":"2011","unstructured":"Pedregosa\u00a0F, Varoquaux\u00a0G, Gramfort\u00a0A, Michel\u00a0V, Thirion\u00a0B, Grisel\u00a0O, Blondel\u00a0M, Prettenhofer\u00a0P, Weiss\u00a0R, Dubourg\u00a0V, Vanderplas\u00a0J, Passos\u00a0A, Cournapeau\u00a0D, Brucher\u00a0M, Perrot\u00a0M, Duchesnay \u00c9 (2011) Scikit-learn: machine learning in Python. J\u00a0Mach Learn Res 12:2825\u20132830","journal-title":"J Mach Learn Res"},{"key":"518_CR31","first-page":"1137","volume":"2","author":"R Kohavi","year":"1995","unstructured":"Kohavi\u00a0R (1995) A\u00a0study of cross-validation and bootstrap for accuracy estimation and model selection. Proc 14th Int Joint Conf Artif Intell 2:1137\u20131143","journal-title":"Proc 14th Int Joint Conf Artif Intell"},{"issue":"1","key":"518_CR32","doi-asserted-by":"publisher","first-page":"5","DOI":"10.1023\/A:1010933404324","volume":"45","author":"L Breiman","year":"2001","unstructured":"Breiman\u00a0L (2001) Random forests. Mach Learn 45(1):5\u201332. https:\/\/doi.org\/10.1023\/A:1010933404324","journal-title":"Mach Learn"},{"issue":"260","key":"518_CR33","doi-asserted-by":"publisher","first-page":"583","DOI":"10.1080\/01621459.1952.10483441","volume":"47","author":"WH Kruskal","year":"1952","unstructured":"Kruskal\u00a0WH, Wallis\u00a0WA (1952) Use of ranks in one-criterion variance analysis. J\u00a0Am Stat Assoc 47(260):583\u2013621","journal-title":"J Am Stat Assoc"}],"container-title":["Datenbank-Spektrum"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s13222-025-00518-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s13222-025-00518-4","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s13222-025-00518-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,6]],"date-time":"2026-02-06T07:52:46Z","timestamp":1770364366000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s13222-025-00518-4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11]]},"references-count":33,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2025,11]]}},"alternative-id":["518"],"URL":"https:\/\/doi.org\/10.1007\/s13222-025-00518-4","relation":{},"ISSN":["1618-2162","1610-1995"],"issn-type":[{"value":"1618-2162","type":"print"},{"value":"1610-1995","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,11]]},"assertion":[{"value":"25 May 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"31 October 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"20 November 2025","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}