Today, omnipresent sensors are continuously providing streaming data on the environments in which they operate. For instance, a typical monitoring and analysis system may use streaming data generated by sensors to monitor the status of a particular device. Analysis and monitoring systems should be designed to make predictions about the future behaviour of the device, or diagnostically infer the most likely system configuration that has produced the observed data. Sources of streaming data with even a modest updating frequency can produce extremely large volumes of data, thereby making efficient and accurate data analysis and prediction difficult. This calls for scalable data analytics.
AMIDST will use two real-world use-cases to rigorously test a set of tools, methods and algorithms to be developed as part of the project on extremely large and highly complex volumes of streaming data. Daimler, which is a partner in the project has provided data for one of the use-cases and will use the results of the project in their development of autonomous driving. The other use-case is provided by the partner BCC, a Spanish Bank, and they will use the developed methods for identifying and evaluating their clients on different parameters.
The AMIDST research project will provide a generic framework for analysis of extremely large volumes of streaming data, thereby adding, creating and increasing the value of existing and new data resources as well as providing a means for more timely and efficient decision making.
AMIDST targets three strategic EU areas: software development, the automotive industry and finance and the combination of academic and industry partners complements the project very well. The academic partners have the knowledge and research facilities to undertake the research and the industry partners has the competences and interest in utilising the results for commercial use.