XAI for CPS - Code and Results
Abstract
These artefacts are utilised within the publication "Explainable AI to Improve Machine Learning
Reliability for Industrial Cyber-Physical Systems". This article explores the use of explainable AI
(XAI) techniques to evaluate machine learning models for a CPS use case. Specifically the C-SHAP
method is applied to interpret CNN predictions on time series data. The use case involves detecting
anomalies (Normal, NoFan, UnderVolt conditions) on an ARM-based computing platform.
The data used by the code can be found here:
https://doi.org/10.5281/zenodo.19135487
Refer to the provided README file for further details.
Metadata
Links
Related artefacts
Licence
Artefacts shared as PDF are licenced under
CC BY 4.0.