Internet of Things (IoT)

“Computational intelligence and network science for the Internet of Things”


Already now, the Internet includes more nodes than there are neurons in the human brain. Many devices are getting increasingly powerful and smarter; yet myriad dumb ‘things’ are populating our digital ecosystem too. By connecting the digital and the physical worlds, the Internet of Things (IoT) is fundamental to addressing major societal problems and has a yearly business potential at the tunes of trillions of dollars. IoT is all about connecting anything, moving data timely, and making correlations across heterogeneous pieces of information. It’s a complex network that rewires much faster than our ability to observe it, and morphs into new patterns continuously. Projections place IoT on the scale of a trillion-node network, generating Zettabyte of data that will be mostly distributed, unstructured, uncorrelated, noisy and incomplete. IoT is certainly  among the most complex data science problems ever tackled.


The realization of IoT systems at scale is a daunting task, involving the digitization of sensing, actuation, and control. Future IoT systems won’t be driven by the deterministic mechanisms of today. They will be sustained by all sorts of intelligent processes, both inside the devices and among them. Things will have the ability to seamlessly interplay but also to survive external perturbations, minimize their digital footprint, self-diagnose, and generally operate based on predictions. Data mining and machine learning will be instrumental to IoT, yet these will evolve from the current cloud-based methods into new decentralized, distributed and lightweight computations.

Research challenges

  1. Data-intensive applications, e.g. smart cities, smart energy, smart health, smart agriculture, smart transport
  2. Data sensing, pre-processing, transmission
  3. Decentralized and hybrid data collection and mining
  4. Dealing with network complexity and inefficiency
  5. Complex events correlation and semantic interoperability
  6. Online machine learning, prediction, and control
  7. Dependable data and communications

Project examples

  • Inter-IoT, EU Horizon 2020
    IoT Interoperability and data mining
  • ACCUS, EU Artemis
    Cooperative control in smart cities
  • DEMANES, EU Artemis
    Monitoring and operation in industrial IoT systems
  • SCOTT, EU Horizon 2020 ECSEL
    Secure COnnected Trustable Things
  • ProHeal, EU ITEA
    Automated Self-Protection and Self-Healing Software Solutions

Facilities & Datasets

We maintain an experimental Open IoT facility, that allows the deployment of applications, cloud-assisted event and data logging and correlation,  IoT data mining, dataset generation and analysis.