{"publication":"Frontiers in Bioengineering and Biotechnology","date_created":"2025-07-31T09:23:31Z","date_updated":"2025-07-31T11:35:20Z","article_type":"original","has_accepted_license":"1","article_number":"1609369","year":"2025","keyword":["in-situ","permittivity","dielectric spectroscopy","signal preprocessing","dynamic threshold","static threshold","anomaly validation","Pichia pastoris"],"publication_status":"published","publisher":"Frontiers Media SA","publication_identifier":{"eissn":["2296-4185"]},"quality_controlled":"1","_id":"13101","title":"Anomaly detection and removal strategies for in-line permittivity sensor signal used in bioprocesses","ddc":["570"],"file":[{"content_type":"application/pdf","file_size":2935650,"file_name":"fbioe-1-1609369.pdf","access_level":"closed","file_id":"13102","creator":"f6x-0e0","relation":"main_file","date_created":"2025-07-31T09:24:49Z","date_updated":"2025-07-31T11:35:18Z"}],"user_id":"83781","volume":13,"author":[{"full_name":"Bolmanis, Emils","first_name":"Emils","last_name":"Bolmanis"},{"last_name":"Uhlendorff","id":"85335","first_name":"Selina","full_name":"Uhlendorff, Selina"},{"orcid":"0000-0002-7920-0595","last_name":"Pein-Hackelbusch","id":"64952","full_name":"Pein-Hackelbusch, Miriam","first_name":"Miriam"},{"last_name":"Galvanauskas","first_name":"Vytautas","full_name":"Galvanauskas, Vytautas"},{"last_name":"Grigs","full_name":"Grigs, Oskars","first_name":"Oskars"}],"citation":{"ieee":"E. Bolmanis, S. Uhlendorff, M. Pein-Hackelbusch, V. Galvanauskas, and O. Grigs, “Anomaly detection and removal strategies for in-line permittivity sensor signal used in bioprocesses,” <i>Frontiers in Bioengineering and Biotechnology</i>, vol. 13, Art. no. 1609369, 2025, doi: <a href=\"https://doi.org/10.3389/fbioe.2025.1609369\">10.3389/fbioe.2025.1609369</a>.","din1505-2-1":"<span style=\"font-variant:small-caps;\">Bolmanis, Emils</span> ; <span style=\"font-variant:small-caps;\">Uhlendorff, Selina</span> ; <span style=\"font-variant:small-caps;\">Pein-Hackelbusch, Miriam</span> ; <span style=\"font-variant:small-caps;\">Galvanauskas, Vytautas</span> ; <span style=\"font-variant:small-caps;\">Grigs, Oskars</span>: Anomaly detection and removal strategies for in-line permittivity sensor signal used in bioprocesses. In: <i>Frontiers in Bioengineering and Biotechnology</i> Bd. 13. Lausanne, Frontiers Media SA (2025)","chicago":"Bolmanis, Emils, Selina Uhlendorff, Miriam Pein-Hackelbusch, Vytautas Galvanauskas, and Oskars Grigs. “Anomaly Detection and Removal Strategies for In-Line Permittivity Sensor Signal Used in Bioprocesses.” <i>Frontiers in Bioengineering and Biotechnology</i> 13 (2025). <a href=\"https://doi.org/10.3389/fbioe.2025.1609369\">https://doi.org/10.3389/fbioe.2025.1609369</a>.","van":"Bolmanis E, Uhlendorff S, Pein-Hackelbusch M, Galvanauskas V, Grigs O. Anomaly detection and removal strategies for in-line permittivity sensor signal used in bioprocesses. Frontiers in Bioengineering and Biotechnology. 2025;13.","apa":"Bolmanis, E., Uhlendorff, S., Pein-Hackelbusch, M., Galvanauskas, V., &#38; Grigs, O. (2025). Anomaly detection and removal strategies for in-line permittivity sensor signal used in bioprocesses. <i>Frontiers in Bioengineering and Biotechnology</i>, <i>13</i>, Article 1609369. <a href=\"https://doi.org/10.3389/fbioe.2025.1609369\">https://doi.org/10.3389/fbioe.2025.1609369</a>","mla":"Bolmanis, Emils, et al. “Anomaly Detection and Removal Strategies for In-Line Permittivity Sensor Signal Used in Bioprocesses.” <i>Frontiers in Bioengineering and Biotechnology</i>, vol. 13, 1609369, 2025, <a href=\"https://doi.org/10.3389/fbioe.2025.1609369\">https://doi.org/10.3389/fbioe.2025.1609369</a>.","havard":"E. Bolmanis, S. Uhlendorff, M. Pein-Hackelbusch, V. Galvanauskas, O. Grigs, Anomaly detection and removal strategies for in-line permittivity sensor signal used in bioprocesses, Frontiers in Bioengineering and Biotechnology. 13 (2025).","short":"E. Bolmanis, S. Uhlendorff, M. Pein-Hackelbusch, V. Galvanauskas, O. Grigs, Frontiers in Bioengineering and Biotechnology 13 (2025).","ufg":"<b>Bolmanis, Emils u. a.</b>: Anomaly detection and removal strategies for in-line permittivity sensor signal used in bioprocesses, in: <i>Frontiers in Bioengineering and Biotechnology</i> 13 (2025).","ama":"Bolmanis E, Uhlendorff S, Pein-Hackelbusch M, Galvanauskas V, Grigs O. Anomaly detection and removal strategies for in-line permittivity sensor signal used in bioprocesses. <i>Frontiers in Bioengineering and Biotechnology</i>. 2025;13. doi:<a href=\"https://doi.org/10.3389/fbioe.2025.1609369\">10.3389/fbioe.2025.1609369</a>","chicago-de":"Bolmanis, Emils, Selina Uhlendorff, Miriam Pein-Hackelbusch, Vytautas Galvanauskas und Oskars Grigs. 2025. Anomaly detection and removal strategies for in-line permittivity sensor signal used in bioprocesses. <i>Frontiers in Bioengineering and Biotechnology</i> 13. doi:<a href=\"https://doi.org/10.3389/fbioe.2025.1609369\">10.3389/fbioe.2025.1609369</a>, .","bjps":"<b>Bolmanis E <i>et al.</i></b> (2025) Anomaly Detection and Removal Strategies for In-Line Permittivity Sensor Signal Used in Bioprocesses. <i>Frontiers in Bioengineering and Biotechnology</i> <b>13</b>."},"type":"scientific_journal_article","status":"public","intvolume":"        13","place":"Lausanne","abstract":[{"lang":"eng","text":"Introduction: In-line sensors, which are crucial for real-time (bio-) process monitoring, can suffer from anomalies. These signal spikes and shifts compromise process control. Due to the dynamic and non-stationary nature of bioprocess signals, addressing these issues requires specialized preprocessing. However, existing anomaly detection methods often fail for real-time applications.\r\n\r\nMethods: This study addresses a common yet critical issue: developing a robust and easy-to-implement algorithm for real-time anomaly detection and removal for in-line permittivity sensor measurement. Recombinant Pichia pastoris cultivations served as a case study. Trivial approaches, such as moving average filtering, do not adequately capture the complexity of the problem. However, our method provides a structured solution through three consecutive steps: 1) Signal preprocessing to reduce noise and eliminate context dependency; 2) Anomaly detection using threshold-based identification; 3) Validation and removal of identified anomalies.\r\n\r\nResults and discussion: We demonstrate that our approach effectively detects and removes anomalies by compensating signal shift value, while remaining computationally efficient and practical for real-time use. It achieves an F1-score of 0.79 with a static threshold of 1.06 pF/cm and a double rolling aggregate transformer using window sizes w1 = 1 and w2 = 15. This flexible and scalable algorithm has the potential to bridge a crucial gap in process real-time analytics and control."}],"language":[{"iso":"eng"}],"file_date_updated":"2025-07-31T11:35:18Z","department":[{"_id":"DEP4028"},{"_id":"DEP4000"}],"doi":"10.3389/fbioe.2025.1609369"}