Since its birth, EMF is being used to guide the development of embedded systems software that is used to control and ensure safety in cars, airplanes and consumer electronics. Many organizations are turning to modeling tools like EMF to automate many of the boring coding tasks associated with developing large software systems. On top this, niche engineering domains are using EMF to validate the architecture and consistency of the instances. As a result, the EMF models for making sense of these systems quickly grew beyond couple of GB.
This exploitation of EMF leads to the collection of huge data from the different engineering domain. In BOSCH we have used machine learning algorithms on these data sets and implemented an in-built AI framework which can generate intelligent models, there by achieving big improvements in efficiency and productivity for tools using EMF as their modelling framework. This new approach improved the productivity of the embedded engineer, and performance of the products.
The goal of this presentation is to demonstrate a tooling set developed to make EMF models more intelligent. The tooling allows models to learn the static and real-time scenarios that they are being used in, and become more intelligent in serving the needs of the user.
We will demonstrate a real use case on how I-EMF (Intelligent EMF) is used to improve the efficiency of the ARTOP tooling platform.
The presentation will include :
- Tooling developed for static learning and real-time teaching
- Tool act like a domain-specific-solutions
- Possibility to provide more user specific Machine Learning Algorithms
- Auto generation of intelligent Item Providers (Prioritization of Menu and Action items on Navigator)
- Intelligent Content Proposals in editors