Predictive Analytics on Data Streams

In today’s digital society, the Internet of Things (IoT) is producing significant quantities of data at an unprecedented rate, e.g. in manufacturing or health care.

The omnipresence of sensors and connectivity generates an explosive growth of data that offers the potential for a revolutionary transformation. The analysis of data streams coming from sensors and mobile devices is nowadays still underexplored and offers a lot of exciting opportunities to enrich systems and make them smarter by running data-driven applications.

More specifically, predictive analytics is considered to be one of the key drivers of innovation in the working of such systems. The functioning of these systems can greatly benefit from insights and actionable knowledge that can be extracted out of this data, such as events or anomalies.

Despite the availability of large quantities of data, data processing technologies based on machine learning have not quite matured equally and the transformation of data into actionable knowledge remains a complex task.


Tom Dhaene, Dirk Deschrijver, Erik Mannens, Azarakhsh Jalavand


Ivo Couckuyt, Joeri Ruyssinck, Roberto Medico, Dieter De Witte, Dieter De Paepe, Femke Ongenae, Gilles Vandewiele


  • SBO HYMOP: “HYMOP: hypermodelling strategies on multi-stream time-series data for operational optimization”
  • ICON SENCOM: “Smart energy consumption in manufacturing”
  • EU H2020 AUTOWARE: “Wireless Autonomous, Reliable and Resilient ProductIon Operation ARchitecture for Cognitive Manufacturing”
  • "On-going bilateral collaboration with Ghent University Hospital on predictive analytics for Big Intensive Care data"
  • SBO SMILE-IT: Stable MultI-agent LEarnIng for neTworks

Key publications

Extraction and analysis of time series data from physiological parameters
Extraction and analysis of time series data from physiological parameters