Motivation

Currently available networked embedded systems, Internet-of-Things systems and networks of wearable devices generally rely on sophisticated sensors to gather data from an environment, communicate to exchange information and build services/applications on the top of acquired sensor data. However, the acquired data are not rarely inaccurate due to calibration problems, inefficiencies in the compensation mechanisms, presence of soft and hard faults or changes in the environment in which the devices/embedded systems are operating. These inaccuracies in the acquired data streams might heavily affect the application/service leading to a (possibly relevant) degradation of the performance and Quality-of-Service. Moreover, recent cyberattacks and privacy leaks affecting IoT and distributed systems underscore the importance of designing security and privacy policies for CPSs.

To address these critical issues, in recent years, research has focused on Intelligent Cyber-Physical Systems (ICPSs) that are cyber-physical systems endowed with intelligent abilities. The main characteristic of such a new generation of distributed embedded systems is the ability to interact with the environment and adapt to new working conditions through distributed intelligent mechanisms operating at the unit (single device), cluster (groups of devices) and network level (the network of devices). Such ICPSs rely on machine learning and computational intelligent solutions to analyze and interpret the data acquired from the environment and activate proper reaction/control mechanisms to guarantee the QoS of the application. In addition, such ICPSs must consider privacy and security intelligent mechanisms to support privacy-preserving learning (so as to avoid privacy leaks) and intelligent cyber-security (machine learning based approaches to the security protection and observation of ICPSs attacks).

For the aforementioned reasons, the TF on “Intelligent Cyber-Physical Systems” perfectly fits the scope of the SWTC by studying CI techniques meant to operate in distributed (embedded) devices characterized by constraints on memory, computation, energy and communication bandwidth and are designed to deal with uncertainties related to the interaction (gathering data/actions) with a real environment through sensors/actuators. The TF is meant to operate vertically on the main four aspects of the SMTC (i.e., Smart Objects and Interactions, Smart Systems and Services, Smart Environments and Applications, Smart Things related to Personalization and Social Aspects) by studying the use of intelligent mechanisms on all levels of a CPS (from the object-layer through the system-layer up to the application layer).