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:
Refer to the provided README file for further details.
Metadata
Links
Licence
Artefacts shared as PDF are licenced under
CC BY 4.0.