Lidia Fotia

High-availability (HA) systems—essential in many contemporary contexts—are designed to guarantee the availability of processes and data for more than 99% of their operational time. These systems are typically implemented as Cloud/Edge infrastructures that are properly maintained by human operators and intelligent agents in order to guarantee the required level of availability. Moreover, we are witnessing the widespread adoption of AI-based automation across many industries. AI-based software agents are increasingly being adopted to introduce more automation in highly available systems, particularly for monitoring and fault detection, fault prediction, recovery, and optimization processes. In this review paper, we discuss the state of the art of AI-based solutions for HA systems. In particular, we focus on the use of AI for the core operational mechanisms of monitoring, failure detection, and recovery. Our discussion begins by reviewing a few key background concepts of HA architectures, then we review recent work on AI-based solutions for monitoring, fault detection and recovery in HA systems.

Counting individuals in highly crowded environments, characterized by thousands of people, has garnered significant attention in recent years, due to the high number of vertical markets wherein such algorithms can prove beneficial, ranging from smart city and transportation to retail sectors, among others. Within this context, in this paper we introduce a novel training methodology tailored for estimating the number of people, ensuring precise counting accuracy in both moderately and highly crowded scenarios. The proposed approach exploits a formulation of the problem based on point detection, where each point represents an individual’s head. Our innovative contributions center around the designing of a novel training strategy employing Curriculum Learning (CL), which aims to replicate the gradual learning process observed in human cognition, training on simpler tasks at the beginning and tackling more complex tasks as the training evolves. In order to evaluate the complexity of each sample image, we propose a novel indicator taking into account both the number of people and their distribution within the image. The experimentation phase encompassed 18 publicly available datasets; the obtained results validate the effectiveness of the proposed approach, surpassing the baseline state-of-the-art point detection by 71% and 70% in terms of Mean Absolute Error (MAE) and Mean Squared Error (MSE), respectively

The Internet of Things (IoT) aims to enable a scenario where smart objects, inserted into information networks, supply smart services for human beings. The introduction of edge computing in IoT can reduce the decision-making latency, save bandwidth resources, and expand the cloud services to be allocated at the network’s edge. However, edge-based IoT systems currently face challenges in their decentralized trust management. Trust management is essential to obtain reliable mining and data fusion, improved user privacy and data security, and provisioning of services with context-awareness. In this survey, we first examine the edge-based IoT architectures currently reported in the literature. Then a complete review of trust requirements in edge-based IoT systems is produced. Also, we discuss about blockchain as a solution to solve several trust problems in IoT and analyze in detail the correlation between blockchain and edge computing. Finally, we provide a detailed analysis of performance aspects of trusted edge-based IoT systems and recommend promising research directions.

The introduction of the IoT technology and its pervasive penetration in our daily life implies that IoT smart objects can often participate in social events, and in this case their paradigm of interaction is commonly denoted as social IoT (SIoT). To make reliable transactions into a SIoT scenario, in this article, we introduce a multi-agent SIoT architecture, which integrates a reputation system based on a clustering of the SOs. In our framework, when a SO looks for a resource and detects a reliable partner having that resource, then the two SOs can interact to make a transaction, and at the end of the transaction each of them provides a feedback about the partner to the local reputation system of the edge server, to update the SOs’ reputation scores. Moreover, each edge server sends these reputation scores to the cloud, which updates the associated reputation values of the SOs, deriving from experiences coming from all the edge domains. This architecture provides a given object, moving from an edge domain to another one, with the possibility to have an updated value of its reputation, represented by the value stored in the cloud. We have validated our approach by a campaign of simulations, whose results seem particularly promising.