Szczegóły publikacji
Opis bibliograficzny
Machinery activity recognition in the industry based on heterogeneous data / Marta PODOBIŃSKA-STANIEC, Marek KĘSEK, Edyta BRZYCHCZY // W: Business Process Management workshops : BPM 2024 international workshops : Krakow, Poland, September 1–6, 2024 : revised selected papers / eds. Katarzyna Gdowska, María Teresa Gómez-López, Jana-Rebecca Rehse. — Cham : Springer Nature, cop. 2025. — (Lecture Notes in Business Information Processing ; ISSN 1865-1348 ; LNBIP 534). — ISBN: 978-3-031-78665-5; e-ISBN: 978-3-031-78666-2. — S. 125-137. — Bibliogr. s. 134-137, Abstr. — Publikacja dostępna online od: 2025-02-20. -- Opubl. w ramach: 8th international workshop on Business Processes Meet Internet-of-Things (BP-Meet-IoT 2024)
Autorzy (3)
Słowa kluczowe
Dane bibliometryczne
| ID BaDAP | 158383 |
|---|---|
| Data dodania do BaDAP | 2025-03-26 |
| DOI | 10.1007/978-3-031-78666-2_10 |
| Rok publikacji | 2025 |
| Typ publikacji | materiały konferencyjne (aut.) |
| Otwarty dostęp |  |
| Wydawca | Springer |
| Konferencja | International Conference in Business Process Management 2024 |
| Czasopismo/seria | Lecture Notes in Business Information Processing |
Abstract
Nowadays, machinery is getting much more complex and equipped with various sensors providing data about actual process execution. One of the directions of machinery data usage is activity recognition, which can be used in process modeling and analysis, enabling process improvements. We aimed to summarize machinery activity recognition (MAR) implementations in the industry. We formulated four research questions concerning MAR applications in the industrial domains, data sources, analytic approaches, and techniques. We carried out a Systematic Literature Review based on renowned publication databases. We started with 812 papers from Scopus and ISI Web of Science, and after detailed analysis, we finally ended with 29 papers used for data extraction. We discovered that the MAR is a relatively common data-oriented task in the construction industry and can also be noticed in other domains like mining, logistics, and medicine, proving that this kind of analytics has wide applications. Due to the nature of MAR, many papers present a supervised approach with various classifiers, among them, one can find neural networks as the most popular and effective techniques.
