The Internet of Things (IoT) is expected to reach its full potential through actually intelligent and autonomous cyber-physical devices and systems. Along this line, Artificial Intelligence (AI) is likely to be the best source of resources – such as algorithms, technologies, methodologies, and paradigms – enabling the development of next-generation “smart” devices and systems. In fact, the “IoT-AI” combination let us envision a cyber-physical scenario (often referred to as IoIT, i.e., “Internet of Intelligent Things”) where devices compute while interacting with each others, with human users, and with their surrounding environments in a dynamic, adaptive, and cognitive way. This vision is expected to bring great improvements and advantages – as well as, of course, novel challenges – in virtually all applicative contexts, including, but not limited to, Industry 4.0, e-Health, entertainment, logistics, etc.

However, although the premise and the comforting initial results, a decidedly relevant  technical and research work is still lacking before the IoT can effectively promote the next socio-economic revolution. In particular, despite the large body of results and techniques that individually characterize the two areas – IoT and AI – and despite the extensive use of ML for the analysis of the data produced by IoT systems, to date little attention has been paid to provide the interconnected objects with of an actual intelligence that allows them to  recognize the context in which they are located, (ii) interact effectively, flexibly and dynamically with human beings, (iii) interact with each other in ways not a-priori defined by the designers and, hopefully, (iv) opportunistically exploit the situation in which they are immersed and the interactions therein possible to fulfill their own purposes. It is reasonable to expect that great benefits for the IoT can emerge by combining the whole spectrum of AI techniques with the various approaches used in the IoT to distribute data and computation and to exploit the interaction between multiple devices. For this reason, this session aims to explore not only the adaptation of existing AI techniques to the IoT context, but also the development of new specific and original approaches. The session, therefore, aims to collect contributions from the academic and industrial world, to present innovative solutions for the development of intelligent IoT ecosystems as well as new business models and relevant experiences from successful smart applications.

• Theories and formal methods for the analysis and modelling of IIoT systems
• Innovative computational models to support cognitive devices and systems
• Paradigms, methodologies and tools for the development of IIoT ecosystems
• AI for Edge Computing
• Architectures and network protocols for the cognitive IoT
• AI for secure IoT networks and devices
• Big & smart data for the IIoT
• Methods and techniques of automatic reasoning to support for the IoIT
• Advanced Human-Machine Interaction through IoT devices/systems
• Smart Applications for IoT ecosystems
• Services and business models for the IoIT
• General-purpose yet flexible tools for simulating IIoT systems