In a smart city environment, the explosive growth in the volume, speed, and variety of data being produced every day requires a continuous increase in the processing speeds of servers and entire network infrastructures, platforms as well as new resource management models. This poses significant challenges (and provides attractive development opportunities) for data-intensive and high-performance computing, i.e., how to turn enormous datasets into valuable information and meaningful knowledge efficiently. The variety of sources complicates the task of context data management such as data derives from, resulting in different data formats, with varying storage, transformation, delivery, and archiving requirements. At the same time, rapid responses are needed for real-time applications. With the emergence of cloud infrastructures and platforms, achieving highly scalable data management in such contexts is a critical problem, as the overall urban application performance is highly dependent on the properties of the data management service. This means, continuously developing and adopting ICT technologies to create and use platforms for government, business and citizens can communicate and work together and provide the necessary connections between the networks that are the base for the services of the smart city [1]. The main features of a generic Smart City Platform (SCP) are in the following [2].

•Make data, information, people and organizations smarter;

•Redesign the relationships between government, private sector, non-profits, communities and citizens;

•Ensure synergies and interoperability within and across city policy domains and systems (e.g. transportation, energy, education, health & care, utilities, etc.);

•Drive innovation, for example, through so-called open data, living labs and tech-hub.

In this work, the authors propose an approach and describe a methodology and a modular and scalable multi-layered ICT platform called ENEA Smart City Platform (ENEA-SCP) to address the problem of cross-domain interoperability in the context of smart city applications. The ENEA-SCP is implemented following the Software as a Service (SaaS) paradigm, exploiting cloud computing facilities to ensure flexibility and scalability. Interoperability and communication are addressed employing web services, and data format exchange is based on the JSON data format. By taking into account these guidelines as references, this work provides a description of the SCP developed by ENEA and its potential use for smart and IoT city applications. The solution provided by ENEA SCP to exploit potentials in Smart City environments is based on four fundamental concepts: Open Data,

Interoperability, Scalability, Replicability. In this scenario, the ENEA SCP is going to tackle the issues concerning these two aspects providing a reference framework of modular [2] specifications for stakeholders willing to implement ICT platforms to exploit the Smart City vision potentials and therefore offer new services for the citizen. The ENEA Smart City Platform exploits computational resources of the ENEAGRID infrastructure [3], as it is deployed in the cloud hosted in the Portici Research Center site. The creation of a customized environment ENEA cloud-based platform is possible thanks to the virtualization technologies of VMWARE platform, which allows hosting the management, the transportation and the processing of project data services, ensuring their availability and protection over time. More in detail, the SCP is composed by six Virtual Machines (VMs), and each of them hosts a component with a specific role

Changing hydrological conditions are occurring all over the world, owing mostly to phenomena of climate change that affect atmospheric and earth surface processes. Temporal and spatial changes in rainfall have caused fundamental variations in the water cycle, including extremes such as flood events. Losses due to all types of floods are not only of economic nature (several billions of EUR every year at global level) but there is also considerable loss of lives. Responding appropriately to these threatening situations necessitates the use of innovative flood management techniques and technologies more than ever. The main priority of any flood management solution is to find suitable methods and models in order to manage floods better and to prepare facing this natural hazard and risk phenomenon and minimizing losses. Decision making and planning for the prediction of flood events and their generating processes require the use of adequate models and methods. In recent years, appropriate models and algorithms such as machine learning (ML) and deep learning (DL) have been developed and used in many research projects dealing with flood mapping. In this regard, the main purpose of this study is to present a review of applying ML/DL methods to process remotely sensed images for generating flood maps. Moreover, the basic concepts of some ML data driven methods are presented. Three case studies with different ML algorithms have been selected and are illustrated to provide a better understanding of their application in flood studies. The findings of these case studies show that ML models are mostly applied to identify and predict flooded versus non-flooded pixels in images but important challenges remain. These challenges need to be solved if ML is to be valuable for decision making processes related to flood management.

Nowadays, driver monitoring is a topic of paramount importance, because distraction and inattention are a relevant safety concern crashes [1]. Currently, Driver Monitoring Systems collect and process dynamic data from embedded sensors in the vehicle and RGB-D cameras detecting visual distraction and drowsiness, but neglect the driver’s emotional states, despite research demonstrated precisely that emotion and attention are linked, and both have an impact on performances [3]. For instance negative emotions can alter perception and decision-making [4]. Consequently, explaining complicated phenomena such as the effects of emotions on driving and conceiving how to use emotions to decrease distraction need to be explored.

Today several methods and technologies allow the recognition of human emotions, which differ in level of intrusiveness [3]. Invasive instruments based on biofeedback sensors can affect the subjects’ behavior and the experienced emotions. Non-intrusive emotion recognition systems, i.e. those based on speech recognition analysis and facial emotion analysis, implement Convolutional Neural Networks (CNN) for signal processing. However no study has actually tested their effectiveness in a motor vehicle to enable emotion regulation [6].

In this context the research focuses on the introduction of a multimedia sensing network and an affective intelligent interface able to monitor the emotional state and degree of driver’s attention by analyzing the persons’ facial expressions and map the recognized emotions with the car interface in a responsive way to increase human wellbeing and safety. The adopted technology for emotion recognition is reported in [7] and is extended with additional features specific for vehicle environment to implement emotion regulation strategies in the human-machine interface to improve driving safety. The result is an emotion-aware interface able to detect and monitor human emotions and to react in case of hazard, e.g. providing warning and proper stimuli for emotion regulation and even acting on the dynamics of the vehicle. The figure reports the conceptual research framework. This work is part of a long-term project called NEXTPERCEPTION, funded from the European Union’s Horizon 2020 program ECSEL Joint Undertaking (JU) under grant agreement No. 876487.