Thanks to the improvements of nanotechnology and microelectronic technologies, increasingly complex and miniaturized smart sensors and devices are spreading on the market. These smart devices, which are an integral part of the Internet of Things (IoT), are able to capture and elaborate data from the environment, communicate and interact with other systems and with the environment itself, making predictions and finding intelligent solutions based on the application needs.
Smart systems integration concerns the combining of smart devices to merge their functional into a comprehensive and interoperable system. Such systems may be used in different areas such as aeronautics, automotives, security, logistics, health-care, smart grid, predictive maintenance, industrial processes engineering and more. More in general, what is proposed is typically aimed at achieving greater efficiency by optimizing management and processes, reducing the costs and the resources used.
The main aim of this research project is the study, the design and the development of scalable, efficient and reliable machine and statistial learning solutions along with formal methods practices useful for the smart systems integration setting starting from raw sensors data.