A Visualisation Tool for Interpretable Predictive Maintenance
@ Intelligent Systems Lab
GNU General Public License (GPL) v3
This component introduces a visualisation tool incorporating interpretations to display information derived from predictive maintenance models, trained on time-series data.
Research areasExplainable AI
Technical CategoriesMachine learning Robotics and automation
12.06.2021 - 18:31
Install & Run: Please ensure you have docker installed on your desktop. Download the component and then navigate to the subfolder through your terminal. Afterwards:
>>> docker build -t visioreddemo . (The dot is necessary)
After succesfully installing VisioRed, please do:
>>> docker run -p 8866:8866 visioreddemo
Then, in your terminal copy the localhost url and open it in your browser.
Additional information: Explanation techniques: LioNets, LIME, iPCA
- Dataset: https://cutt.ly/7bHM4SO
- Related publication: https://arxiv.org/pdf/2103.17003.pdf (Accepted to IJCAI 2021 Demo Track)
The interpretation technique implemented in VisioRed is intended to provide explanations to predictive maintenance models, towards a trustworthy machine learning component.
VisioRed component is GDPR compliant (Articles 13–15) because it is providing a way to interpret the decision of a neural network model operating in predictive maintenance. This approach addresses the "explicability" requirement of the GDPR, where a requirement is fixed for automated decision processes that have an impact on humans.