Orchestrating microservices in Edge environments presents significant challenges due to the distributed and heterogeneous nature of the infrastructure, as well as the constraints of limited resources and variable connectivity. This paper addresses these issues by proposing a distributed framework for microservice orchestration based on a consensus algorithm. Our approach leverages a leader-follower consensus model, adapted to handle dynamic workloads and resource allocation efficiently. Through an extensive analysis of existing solutions, we identified the limitations of traditional centralized orchestration frameworks in Edge contexts, motivating the need for a decentralized methodology. The proposed framework introduces a dynamic leader election mechanism based on workload priorities and a distributed logging system for enhanced transparency and reliability. We validated our solution through experimental implementation on an Edge cluster composed of Raspberry Pi nodes, demonstrating its ability to adapt dynamically to variable workloads while ensuring consistency and fault tolerance. The results show that the framework effectively balances computational loads and meets the requirements of modern Edge computing applications.

In the last years, we have seen an increase in the number of Artificial Intelligence (AI)-powered applications for information retrieval and data science. This fact led to an increasing reliance on distributed computing infrastructures, including Cloud, Edge, and IoT environments. These architectures enable powerful and scalable solutions but also introduce new security and privacy risks that must be addressed at both the system and data levels. Even a single breach on any of the links of the data-service-infrastructure chain may seriously compromise the security of the end-user application. With such a wide attack surface, security must definitely be approached in a holistic way and addressed in any layer where concerns may potentially arise. SIoTEC solicits novel and innovative ideas, proposals, positions and best practices that address the modelling, design, implementation, and enforcement of security in Cloud/Edge/IoT environments. Workshop website: https://siotec.netsons.org/

This work compares univariate and multivariate Long Short-Term Memory (LSTM) models for predicting delays in public transportation. Only historical delay data was used to train the univariate model, which is effective for last-minute predictions but limited in capturing wider temporal correlations because it is optimized for real-time inference with minimal data requirements. To better capture intricate patterns in transportation delays, the multivariate model incorporates extra contextual factors like time of day and topographical coordinates. Multiple multivariate models were trained on different time intervals (e.g., daily, weekly, and monthly) to evaluate the impact of training data selection on predictive accuracy. The findings show that multivariate models provide better long-term accuracy, especially when trained on properly segmented data, whereas univariate models are computationally efficient and excellent for short-term updates. These results suggest how to best adapt LSTM-based forecasting models for dynamic, practical transportation applications.

The growing diversity of data sources in modern organizations has made efficient querying and integration crucial for actionable insights. With data distributed across structured relational databases like MySQL and semistructured NoSQL systems such as MongoDB, querying heterogeneous environments has become more complex. Apache Drill and PrestoDB are two prominent query engines designed to address this challenge by providing federated querying across multiple data sources. This paper examines the architecture, design, and performance of Apache Drill and PrestoDB, focusing on their integration with MySQL and MongoDB. Using a synthetic smart city dataset that simulates urban mobility, traffic, air quality sensors, and public infrastructure usage, a series of queries, spanning from basic data retrieval to complex multi-source joins and aggregations, were executed to assess each engine’s performance across various workloads. This research provides insights into the trade-offs between flexibility and performance when querying heterogeneous data environments. It also offers guidance for optimizing data retrieval and analysis across various storage systems.

The COVID-19 pandemic was first identified in Wuhan (China) in late 2019, and quickly escalated into a global crisis, emphasizing the need for rapid and accurate diagnostic methods. Since chest X-rays play a key role in diagnosing COVID-19, we applied deep learning techniques to the COVID-19 Radiography Dataset to enhance diagnostic accuracy. These models are trained with augmented data to improve generalization across different radiographic presentations of the virus. The results demonstrate the speed and reliability of COVID-19 diagnosis, helping healthcare systems to make faster treatment decisions. This also supports ongoing efforts to manage COVID-19 and creates a foundation for using Artificial Intelligence to detect future respiratory diseases.

In the last years, our cities become more and more crowded due to the increasing number of cars into old city planes. So, even small/medium cities experience a travel time comparable with the bigger ones. To improve mobility management in modern cities, specific simulation tools can be used to analyze the impact of different mobility plans on mobility and, therefore to find the most suitable solution for each city. However, these tools are often hard to be used by city traffic managers without advanced computer skills. In this article, we used a multiagent transport simulation (MATSim) to provide a simple tool that can be easily used by end-users to better plan mobility strategies for both private and public transportation. In particular, starting from the open data provided by the city of Messina, we have implemented a software tool able to process MATSim events. Moreover, we propose a metric to estimate the safety of roads for cyclists. From the experimental results provided by the proposed software, we are able to discover the most overloaded links and estimate the travel time distribution by hour of departure time.

Monitoring road pavement conditions is vital to prevent harm or accidents to vehicles and people, and it is a crucial governmental task. Some Artificial Intelligence (AI) based systems for automatically detecting and classifying road anomalies have been proposed in the literature. In particular, vision-based Deep Learning techniques process images to analyze the road pavement and detect different types of anomalies, thus offering a very flexible approach to road monitoring. This paper focuses on the comparison of two different vision-based techniques aimed at pothole detection: CNN and R-CNN. We have carried out our experiments by analyzing video streams acquired with a smartphone mounted on the windshield of a vehicle through a car mobile holder. Also, the Deep Learning classification models have been run on different computing infrastructures, such as a Microsoft Azure virtual machine (VM) and an edge device Raspberry Pi, to evaluate the usability in the Cloud and on-road infrastructures.

Internet of Things (IoT) became more and more popular because of the raise of ubiquitous internet connected devices. In this regard, IoT nodes are often organized in wireless sensor networks to facilitate communication and perform a coral computation. Such a network is often employed in urban or rural areas, i.e., for traffic, fires, and floods monitoring. Nodes are, therefore, deployed in remote areas, preventing the possibility to frequently access them, i.e., for firmware update. In this context, over-the-air (OTA) firmware update is used to remotely change the behavior of one or more nodes. In this paper, we firstly build a wireless mesh network with microcontrollers (i.e., ESP32) and, therefore, propose a secure filtered O TA firmware update involving firmware freshness (i.e., quarantine when firmware is not up-to-date), key pairing, and digital signature for data integrity and non-repudiation. The system is evaluated in terms of deactivation time $(s)$, energy consumption $(kWh)$, and greenhouse gases $(\mathrm{kgCO}_{2}\mathrm{e})$, highlighting good results in terms of scalability for grouped updates.

Complex traffic dynamics can be modeled in real time through simulation models and methods which are attracting more and more research efforts. In particular, agent-based models based on agent behaviors with local plans or strategies can be useful for transportation study areas. These models can be used to solve real-world policy problems simulating certain regions or cities. In this paper, we implemented an agent-based transport model for analyzing traffic in the metropolitan city of Messina (Sicily, Italy). We created a scenario using (i) the Messina road network information from OpenStreetMap, (ii) public transport supply data of the Municipality of Messina from General Transit Feed Specification, and (iii) census data related to the six districts of Messina. Then, we made a preliminary analysis of the generated simulation output computing average travel time by agent trip mode, average activity duration and link volumes. Our scenario can be extended and adapted to solve specific problems related to the mobility of individuals in Messina.

Social Network Analysis (SNA) is an interdisciplinary science that focuses on discovering the patterns of individuals interactions. In particular, practitioners have used SNA to describe and analyze criminal networks to highlight subgroups, key actors, strengths and weaknesses in order to generate disruption interventions and crime prevention systems. In this paper, the effectiveness of a total of seven disruption strategies for two real Mafia networks is investigated adopting SNA tools. Three interventions targeting actors with a high level of social capital and three interventions targeting those with a high human capital are put to the test and compared between each other and with random node removal. Similar tests on artificial model networks have also been carried out. Simulations show that actor removal based on social capital proves to be the most effective strategy, by leading to the total disruption of the criminal network in the least number of steps. The removal of a specific figure of a Mafia family such as the Caporegime seems also promising in the network disruption.