Szczegóły publikacji
Opis bibliograficzny
Visual patterns in an interactive app for analysis based on control charts and SHAP values / Iwona Grabska-Gradzińska, Maciej SZELĄŻEK, Szymon Bobek, Grzegorz J. Nalepa // W: Artificial intelligence : ECAI 2023 international workshop : XAI${^{\wedge}}$3, TACTIFUL, XI-ML, SEDAMI, RAAIT, AI4S, HYDRA, AI4AI : Kraków, Poland, September 30 – October 4, 2023 : proceedings, Pt. 2 / eds. Sławomir Nowaczyk, Przemysław Biecek, Neo Christopher Chung, Mauro Vallati, Paweł Skruch, Joanna Jaworek-Korjakowska, Simon Parkinson, Alexandros Nikitas, Martin Atzmüller, Tomáš Kliegr, Ute Schmid, Szymon Bobek, Nada Lavrac, Marieke Peeters, Roland van Dierendonck, Saskia Robben, Eunika Mercier-Laurent, Gülgün Kayakutlu, Mieczysław Lech Owoc, Karl Mason, Abdul Wahid, Pierangela Bruno, Francesco Calimeri, Francesco Cauteruccio, Giorgio Terracina, Diedrich Wolter, Jochen L. Leidner, Michael Kohlhase, Vania Dimitrova. — Cham : Springer Nature Switzerland, cop. 2024. — (Communications in Computer and Information Science ; ISSN 1865-0929 ; CCIS 1948). — ISBN: 978-3-031-50484-6; e-ISBN: 978-3-031-50485-3. — S. 48–59. — Bibliogr., Abstr. — Publikacja dostępna online od: 2024-01-25
Autorzy (4)
- Grabska-Gradzińska Iwona
- AGHSzelążek Maciej
- Bobek Szymon
- Nalepa Grzegorz
Słowa kluczowe
Dane bibliometryczne
ID BaDAP | 151693 |
---|---|
Data dodania do BaDAP | 2024-03-13 |
DOI | 10.1007/978-3-031-50485-3_4 |
Rok publikacji | 2024 |
Typ publikacji | materiały konferencyjne (aut.) |
Otwarty dostęp | |
Wydawca | Springer |
Konferencja | 26th European Conference on Artificial Intelligence |
Czasopismo/seria | Communications in Computer and Information Science |
Abstract
The aim of this paper is to describe the tool for combining the information of control charts, widely used for statistical quality control with the information obtained from the process of explanation the classification decision made using the machine learning model. Control charts are used to monitor production and show deviations from normal behavior, especially when upper and lower control limits of measured parameters are defined. Analysis of SHAP explanations allowed us to show some dependencies of classification process. Our application, which allows the user to compare the information taken from both control charts and SHAP plots, helps the user discover anomalies, especially dependencies between exceeding the limits of controlled parameters and the relevance of these values in SHAP calculations.