Automated, Standardized, and Adaptive Abstraction of IoT Data into Process-Level Events. Brzychczy, E., Beyel, H. H., Grüger, J., Kluza, K., Malburg, L., Meroni, G., & Valderas, P. In Maldonado, A., Bertrand, Y., & Seiger, R., editors, Proceedings of the 10th International Workshop on Business Processes Meet the Internet of Things (BP-Meet-IoT 2026) co-located with the 30th International Conference on Enterprise Design, Operations, and Computing (EDOC 2026), Enschede, The Netherlands, September 15, 2026, volume 4310, of CEUR Workshop Proceedings, 2026. CEUR-WS.org.. ![Automated, Standardized, and Adaptive Abstraction of IoT Data into Process-Level Events [pdf]](https://bibbase.org/img/filetypes/pdf.svg "pdf")
Paper doi abstract bibtex The increasing use of Internet of Things (IoT) technologies in industrial and cyber-physical environments creates new opportunities for process mining, but also reveals a fundamental data challenge. While IoT systems generate large volumes of heterogeneous, low-level sensor data, process mining requires structured event logs with cases, activities, timestamps, and attributes. This paper investigates the problem of converting raw IoT data into process-level event logs as a key research challenge at the intersection of business process management and IoT. It structures the problem into several dimensions, including automated event recognition, case identification, semantic modeling, IoT-enriched event log formats, adaptive abstraction mechanisms, and the role of large language models in abstraction pipelines. Based on our review of the state of the art, the paper identifies major research gaps, such as limited automation and adaptability, insufficient support for temporal dynamics and explainability, fragmented end-to-end solutions, and the lack of benchmark datasets and reproducible evaluation methods. Finally, it also outlines recommendations to guide future work toward more reliable and reusable IoT-driven process mining solutions.
@inproceedings{BrzychczyEtAl2026_IoTAbstraction,
author = {Edyta Brzychczy and Harry H. Beyel and Joscha Grüger and Krzysztof Kluza and Lukas Malburg and Giovanni Meroni and Pedro Valderas},
editor = {Andrea Maldonado and Yannis Bertrand and Ronny Seiger},
title = {{Automated, Standardized, and Adaptive Abstraction of IoT Data into Process-Level Events}},
booktitle = {Proceedings of the 10th International Workshop on Business Processes Meet the Internet of Things (BP-Meet-IoT 2026) co-located with the 30th International Conference on Enterprise Design, Operations, and Computing (EDOC 2026), Enschede, The Netherlands, September 15, 2026},
series = {{CEUR} Workshop Proceedings},
volume = {4310},
publisher = {CEUR-WS.org.},
abstract = {The increasing use of Internet of Things (IoT) technologies in industrial and cyber-physical environments creates new opportunities for process mining, but also reveals a fundamental data challenge. While IoT systems generate large volumes of heterogeneous, low-level sensor data, process mining requires structured event logs with cases, activities, timestamps, and attributes. This paper investigates the problem of converting raw IoT data into process-level event logs as a key research challenge at the intersection of business process management and IoT. It structures the problem into several dimensions, including automated event recognition, case identification, semantic modeling, IoT-enriched event log formats, adaptive abstraction mechanisms, and the role of large language models in abstraction pipelines. Based on our review of the state of the art, the paper identifies major research gaps, such as limited automation and adaptability, insufficient support for temporal dynamics and explainability, fragmented end-to-end solutions, and the lack of benchmark datasets and reproducible evaluation methods. Finally, it also outlines recommendations to guide future work toward more reliable and reusable IoT-driven process mining solutions.},
keywords = {Process Mining in IoT, Event Abstraction, IoT Event Logs, Case Identification, Sensor Data Analytics},
year = {2026},
doi = {10.83095/ceurws_04310_005},
url = {https://www.wi2.uni-trier.de/shared/publications/2026_BPMeetIoT_BrzychczyEtAl.pdf}
}
Downloads: 0
{"_id":"wGBjuvNwkHuC59Jg8","bibbaseid":"brzychczy-beyel-grger-kluza-malburg-meroni-valderas-automatedstandardizedandadaptiveabstractionofiotdataintoprocesslevelevents-2026","author_short":["Brzychczy, E.","Beyel, H. H.","Grüger, J.","Kluza, K.","Malburg, L.","Meroni, G.","Valderas, P."],"bibdata":{"bibtype":"inproceedings","type":"inproceedings","author":[{"firstnames":["Edyta"],"propositions":[],"lastnames":["Brzychczy"],"suffixes":[]},{"firstnames":["Harry","H."],"propositions":[],"lastnames":["Beyel"],"suffixes":[]},{"firstnames":["Joscha"],"propositions":[],"lastnames":["Grüger"],"suffixes":[]},{"firstnames":["Krzysztof"],"propositions":[],"lastnames":["Kluza"],"suffixes":[]},{"firstnames":["Lukas"],"propositions":[],"lastnames":["Malburg"],"suffixes":[]},{"firstnames":["Giovanni"],"propositions":[],"lastnames":["Meroni"],"suffixes":[]},{"firstnames":["Pedro"],"propositions":[],"lastnames":["Valderas"],"suffixes":[]}],"editor":[{"firstnames":["Andrea"],"propositions":[],"lastnames":["Maldonado"],"suffixes":[]},{"firstnames":["Yannis"],"propositions":[],"lastnames":["Bertrand"],"suffixes":[]},{"firstnames":["Ronny"],"propositions":[],"lastnames":["Seiger"],"suffixes":[]}],"title":"Automated, Standardized, and Adaptive Abstraction of IoT Data into Process-Level Events","booktitle":"Proceedings of the 10th International Workshop on Business Processes Meet the Internet of Things (BP-Meet-IoT 2026) co-located with the 30th International Conference on Enterprise Design, Operations, and Computing (EDOC 2026), Enschede, The Netherlands, September 15, 2026","series":"CEUR Workshop Proceedings","volume":"4310","publisher":"CEUR-WS.org.","abstract":"The increasing use of Internet of Things (IoT) technologies in industrial and cyber-physical environments creates new opportunities for process mining, but also reveals a fundamental data challenge. While IoT systems generate large volumes of heterogeneous, low-level sensor data, process mining requires structured event logs with cases, activities, timestamps, and attributes. This paper investigates the problem of converting raw IoT data into process-level event logs as a key research challenge at the intersection of business process management and IoT. It structures the problem into several dimensions, including automated event recognition, case identification, semantic modeling, IoT-enriched event log formats, adaptive abstraction mechanisms, and the role of large language models in abstraction pipelines. Based on our review of the state of the art, the paper identifies major research gaps, such as limited automation and adaptability, insufficient support for temporal dynamics and explainability, fragmented end-to-end solutions, and the lack of benchmark datasets and reproducible evaluation methods. Finally, it also outlines recommendations to guide future work toward more reliable and reusable IoT-driven process mining solutions.","keywords":"Process Mining in IoT, Event Abstraction, IoT Event Logs, Case Identification, Sensor Data Analytics","year":"2026","doi":"10.83095/ceurws_04310_005","url":"https://www.wi2.uni-trier.de/shared/publications/2026_BPMeetIoT_BrzychczyEtAl.pdf","bibtex":"@inproceedings{BrzychczyEtAl2026_IoTAbstraction,\n author = {Edyta Brzychczy and Harry H. Beyel and Joscha Grüger and Krzysztof Kluza and Lukas Malburg and Giovanni Meroni and Pedro Valderas},\n editor = {Andrea Maldonado and Yannis Bertrand and Ronny Seiger},\n title = {{Automated, Standardized, and Adaptive Abstraction of IoT Data into Process-Level Events}},\n booktitle = {Proceedings of the 10th International Workshop on Business Processes Meet the Internet of Things (BP-Meet-IoT 2026) co-located with the 30th International Conference on Enterprise Design, Operations, and Computing (EDOC 2026), Enschede, The Netherlands, September 15, 2026},\n series = {{CEUR} Workshop Proceedings},\n volume = {4310},\n publisher = {CEUR-WS.org.},\n abstract = {The increasing use of Internet of Things (IoT) technologies in industrial and cyber-physical environments creates new opportunities for process mining, but also reveals a fundamental data challenge. While IoT systems generate large volumes of heterogeneous, low-level sensor data, process mining requires structured event logs with cases, activities, timestamps, and attributes. This paper investigates the problem of converting raw IoT data into process-level event logs as a key research challenge at the intersection of business process management and IoT. It structures the problem into several dimensions, including automated event recognition, case identification, semantic modeling, IoT-enriched event log formats, adaptive abstraction mechanisms, and the role of large language models in abstraction pipelines. Based on our review of the state of the art, the paper identifies major research gaps, such as limited automation and adaptability, insufficient support for temporal dynamics and explainability, fragmented end-to-end solutions, and the lack of benchmark datasets and reproducible evaluation methods. Finally, it also outlines recommendations to guide future work toward more reliable and reusable IoT-driven process mining solutions.},\n keywords = {Process Mining in IoT, Event Abstraction, IoT Event Logs, Case Identification, Sensor Data Analytics},\n year = {2026},\n doi = {10.83095/ceurws_04310_005},\n url = {https://www.wi2.uni-trier.de/shared/publications/2026_BPMeetIoT_BrzychczyEtAl.pdf}\n}\n\n","author_short":["Brzychczy, E.","Beyel, H. H.","Grüger, J.","Kluza, K.","Malburg, L.","Meroni, G.","Valderas, P."],"editor_short":["Maldonado, A.","Bertrand, Y.","Seiger, R."],"key":"BrzychczyEtAl2026_IoTAbstraction","id":"BrzychczyEtAl2026_IoTAbstraction","bibbaseid":"brzychczy-beyel-grger-kluza-malburg-meroni-valderas-automatedstandardizedandadaptiveabstractionofiotdataintoprocesslevelevents-2026","role":"author","urls":{"Paper":"https://www.wi2.uni-trier.de/shared/publications/2026_BPMeetIoT_BrzychczyEtAl.pdf"},"keyword":["Process Mining in IoT","Event Abstraction","IoT Event Logs","Case Identification","Sensor Data Analytics"],"metadata":{"authorlinks":{}}},"bibtype":"inproceedings","biburl":"www.wi2.uni-trier.de/publications/WI2Publikationen.bib","dataSources":["bAMYx3JhPtNSnYD4y","9v4v84gbRB6iyKeHb","FWPbCYSxS5WYzo747"],"keywords":["process mining in iot","event abstraction","iot event logs","case identification","sensor data analytics"],"search_terms":["automated","standardized","adaptive","abstraction","iot","data","process","level","events","brzychczy","beyel","grüger","kluza","malburg","meroni","valderas"],"title":"Automated, Standardized, and Adaptive Abstraction of IoT Data into Process-Level Events","year":2026}