New RapidMiner research project - dealing with real-time, interactive extreme-scale analytics
The EU-funded INFORE project held its Kick-off meeting on the 16th of January in Athens, Greece. The RapidMiner research team participated in the 3-day meetings together with all project partners, namely ATHENA – Research and Innovation Center (coordinator), NCSR Demokritos, MarineTraffic, Barcelona Supercomputing Center, The Centre for Genomic Regulation, Spring Techno, NATO Centre of Maritime Research and Experimentation (CMRE) and RapidMiner. The project Kick-off Meeting took place at the Royal Olympic Hotel in Athens, Greece.
The aim of the INFORE project is to address the challenges posed by huge datasets and pave the way for real-time, interactive extreme-scale analytics and forecasting. Today, at an increasing rate, industrial and scientific institutions need to deal with massive data flows, streaming-in from a multitude of sources. For instance, maritime surveillance applications need to combine high-velocity data streams, including vessel position signals transmitted from hundreds of thousands of vessels across the world and acoustic signals of autonomous, unmanned vehicles; in the financial domain, stock price forecasting and portfolio management rely on stock tick data combined with rich, real-time information sources on various pricing indicators; at the forefront of the fight against cancer, complex simulations of multi-cellular systems are used, producing extreme-scale data streams in an effort to predict the effects of drug synergies on cancer cells, and identify personalized combinations of drugs which can ultimately increase the patients’ life expectancy. The ability to forecast, as early as possible, a good approximation to the outcome of a time-consuming and resource demanding computational task allows to quickly identify undesired outcomes and save valuable amount of time, effort and computational resources, which would otherwise be spent in vain.
Together with all project partners, RapidMiner will build the architecture to handle the large amount of data and design the interface to allow an easy interaction with the data processing components. One of the challenges will be to scale the intuitive design of process work flows, known from other RapidMiner products, to the large data streams we plan to handle within INFORE. Therefore, we plan to build new methods to handle and manipulate streaming data and incorporate RapidMiner in an extreme scale computation environment. We are also excited to work on such diverse and interesting use case domains, which have the potential benefit the society at large.
The project will be an adaption of the RapidMiner credo Real Data Science fast and simple to Big Data Science fast and simple.
The project is funded by European Commission under Horizon 2020 Programme, under grant agreement No 825070, and spans on the period January 2019 – December 2021.