WEBINAR #2 - Automotive data analytics with EVOLVE
This webinar organized by EVOLVE partners' VIF and KOOLA is about solving four specific challenges of automotive data analytics using the EVOLVE platform:
(1) Predictive vehicle maintenance from vehicle operation and vehicle maintenance data
(2) Assistance systems status detection from video streams of a vehicle dashboard
(3) Pattern detection in parsimonious vehicle sensor measurements.
(4) Distracted driving detection from driver camera footage.
The webinar outlines data science challenges that are typical for the automotive sector and shows the solutions created in the EVOLVE projects.
For instance, predictive maintenance aims to identify vehicle maintenance issues before they occur. By leveraging data from warranty repairs with current vehicle sensor data, predictive data analytics can find meaningful correlations that would be difficult for a human to discover. Different approaches are possible when talking about predictive maintenance. One of them could be to monitor general signal deviations of units inside a population or fleet of vehicles. The best option seems to be ML (Machine Learning) model based on a combination of DTC codes and available OBD car data. Six different model algorithms (linear and nonlinear) were considered, and the best model is chosen that can be consumed via API.
Demos will be shown of how the EVOLVE platform was used to deploy the data analysis workflow and how the analysis process was accelerated.
Visit our website to know more: www.evolve-h2020.eu
Follow EVOLVE in social media:
Twitter (@Evolve_H2020): / evolve_h2020
LinkedIn: / evol. .
EVOLVE has received funding from the European Union’s Horizon 2020 research and innovation programme under grant agreement No 825061.