A new industrial revolution is undergoing, based on a number of technological paradigms. The will to foster and guide this phenomenon has been summarized in the expression “Industry 4.0” (I4.0). Initiatives under this term share the vision that many key technologies underlying Cyber-Physical Systems and Big Data Analytics are converging to a new distributed, highly automated, and highly dynamic production network, and that this process needs regulatory and cultural advancements to effectively and timely develop. In this work, we focus on the technological aspect only, highlighting the unprecedented complexity of I4.0 emerging from the scientific literature. While previous works have focused on one or up to four related enablers, we consider ten technological enablers, including besides the most cited Big Data, Internet of Things, and Cloud Computing, also others more rarely considered as Fog and Mobile Computing, Artificial Intelligence, Human-Computer Interaction, Robotics, down to the often overlooked, very recent, or taken for granted Open-Source Software, Blockchain, and the Internet. For each we explore the main characteristics in relation to I4.0 and its interdependencies with other enablers. Finally we provide a detailed analysis of challenges in leveraging each of the enablers in I4.0, evidencing possible roadblocks to be overcome and pointing at possible future directions of research. Our goal is to provide a reference for the experts in some of the technological fields involved, for a reconnaissance of integration and hybridization possibilities with other fields in the endeavor of I4.0, as well as for the laymen, for a high-level grasp of the variety (and often deep history) of the scientific research backing I4.0.

Cloud computing and Internet of Things (IoT), two very different technologies, are both already part of our life. Their massive adoption and use is expected to increase further, making them important components of the Future Internet. A novel paradigm where Cloud and IoT are merged together is foreseen as disruptive and an enabler of a large number of application scenarios. In this paper we focus our attention on the integration of Cloud and IoT, which we call the CloudIoT paradigm. Many works in literature have surveyed Cloud and IoT separately: their main properties, features, underlying technologies, and open issues. However, to the best of our knowledge, these works lack a detailed analysis of the CloudIoT paradigm. To bridge this gap, in this paper we review the literature about the integration of Cloud and IoT. We start analyzing and discussing the need for integrating them, the challenges deriving from such integration, and how these issues have been tackled in literature. We then describe application scenarios that have been presented in literature, as well as platforms -- both commercial and open source -- and projects implementing the CloudIoT paradigm. Finally, we identify open issues, main challenges and future directions in this promising field.

The increasing diffusion of mobile devices has dramatically changed the network traffic landscape, with Traffic Classification (TC) surging into a fundamental role while facing new and unprecedented challenges. The recent and appealing adoption of Deep Learning (DL) techniques has risen as the solution overcoming the performance of ML techniques based on tedious and time-consuming handcrafted feature design. Still, the black-box nature of DL models prevents its practical and trustful adoption in critical scenarios where the reliability/interpretation of results/policies is of key importance. To cope with these limitations, eXplainable Artificial Intelligence (XAI) techniques have recently acquired the interest of the community. Accordingly, in this work we investigate trustworthiness and interpretability via XAI-based techniques to understand, interpret and improve the behavior of state-of-the-art multimodal DL traffic classifiers. The proposed methodology, as opposed to common results seen in XAI, attempts to provide global interpretation, rather than sample-based ones. Results, based on an open dataset, allow to complement the above findings with domain knowledge.