PROTEUS mission is to investigate and develop ready-to-use scalable online machine learning algorithms and real-time interactive visual analytics to deal with extremely large data sets and data streams.
The foundation for the PROTEUS advances is the use of an optimized implementation of combined batch and streaming processing and building around this later scalable real time processes. The developed algorithms and techniques will form a library to be integrated into an enhanced version of Apache Flink, the EU Big Data platform.
In project PROTEUS, DFKI works together with industrial and academic partners Bournemouth University, treelogic, Trilateral Research&Consulting, Arcelor Mittal and Lambdoop to develop innovative data analytics algorithms to tackle challenges facing predictive and decision support as well as data visualization.
In particular, the project goes beyond the current state-of-art technology by making the following specific original contributions:
- New strategies for real-time hybrid computation, batch data and data streams.
- Real-time scalable machine learning for massive, high-velocity and complex data streams analytics.
- Real-time interactive visual analytics for Big Data.
- Implementation of the new advances on top of Apache Flink.
- Real-world industrial validation of the technology developed.
DFKI chairs the project's scientific and technical committee, which assists the steering board and project coordinator, and lead development of a high-throughput, low-latency software architecture for conjoint batch and stream processing. Apache Flink is being extended to serve as basis for novel scalable online machine learning algorithms. DFKI will disseminate and exploit scientific results and engage in the Apache Flink community to attract public awareness to PROTEUS.
The project is funded by the European Union (Horizon 2020, Ref: 687691).