Szczegóły publikacji
Opis bibliograficzny
Machine learning techniques for explaining air pollution prediction / Maciej Kusy, Piotr A. KOWALSKI, Marcin Szwagrzyk, Aleksander Konior // W: IJCNN 2022 [Dokument elektroniczny] : International Joint Conference on Neural Networks : Padua, Italy, 18–23 July 2022 : proceedings / IEEE. — Wersja do Windows. — Dane tekstowe. — Piscataway : IEEE, cop. 2022. — (Proceedings of ... International Joint Conference on Neural Networks ; ISSN 2161-4393). — Konferencja zorganizowana w ramach IEEE World Congress on Computational Intelligence (IEEE WCCI 2022). — e-ISBN: 978-1-7281-8671-9. — S. [1–8]. — Wymagania systemowe: Adobe Reader. — Bibliogr. s. [8], Abstr. — Publikacja dostępna online od: 2022-09-30
Autorzy (4)
- Kusy Maciej
- AGHKowalski Piotr Andrzej
- Szwagrzyk Marcin
- Konior Aleksander
Słowa kluczowe
Dane bibliometryczne
ID BaDAP | 142999 |
---|---|
Data dodania do BaDAP | 2022-10-29 |
Tekst źródłowy | URL |
DOI | 10.1109/IJCNN55064.2022.9891994 |
Rok publikacji | 2022 |
Typ publikacji | materiały konferencyjne (aut.) |
Otwarty dostęp | |
Wydawca | Institute of Electrical and Electronics Engineers (IEEE) |
Konferencja | International Joint Conference on Neural Networks |
Czasopismo/seria | Proceedings of ... International Joint Conference on Neural Networks |
Abstract
Explaining the results provided by a machine learning model is crucial in the context of its application in prediction problems. Unfortunately, in itself, it is usually a black box whose interpretation is very difficult. The prediction output generated by the ML model is clear, while its significance - not often sufficient. However, such an outcome can be explained by applying the Shapley analysis. In the current study, this analysis, along with the random forest model, will be used to explain the problem of air pollution prediction measured by the particulate matter 10 (PM10) indicator. The input data will be the meteorological information recorded from October 2021 to December 2021 in four European cities: London, Barcelona, Berlin and Krakow. On the basis of the obtained results, it will be shown what factors and how affect the level of PM10. The presented study stresses the importance of air pollution investigation and contributes to the increase of ecological awareness.