This study focuses on Digital Twin-integrated smart energy systems, which serve as an example of Next-Generation Critical Infrastructures (CI). The resilience of these systems is influenced by a variety of internal features and external interactions, all of which are subject to change following cyber-physical disturbances. This necessitates real-time resilience monitoring for CI during crises; however, a significant gap remains in resilience monitoring. To address this gap, this study leverages the role of Internet of Things (IoT) in monitoring complex systems to enhance resilience through critical indicators relevant to cyber-physical safety and security. The study empirically implements Resilience-Key Performance Indicators (R-KPIs) from the domain, including Functionality Loss, Minimum Performance, and Recovery Time Duration. The main goal is to examine real-time IoT-based resilience monitoring in a real-life context. A cyber-physical system equipped with IoT-driven Digital Twins, data-driven microservices, and a False Data Injection Attack (FDIA) scenario is simulated to assess the real-time resilience of this smart system. The results demonstrate that real-time resilience monitoring provides actionable insights into resilience performance based on the selected R-KPIs. These findings contribute to a systematic and reusable model for enhancing the resilience of IoT-enabled CI, advancing efforts to ensure service continuity and secure essential services for society.

The increase in consumer expectations in terms of comfort and safety accelerated the development of Advanced Driver Assistance Systems (ADAS), which represent an intermediate but fundamental step towards complete vehicle automation. In parallel, the progress in the field of data-driven algorithms and machine learning has allowed for important advancements in the research and development of autonomous driving systems. We focus on the verification and validation of the software for ADAS, with the objective of ensuring compliance with international regulations and safety standards, and propose a solution that aims to overcome traditional rule-based approaches for the validation of ADAS functionalities. In particular, we investigate an automated validation process based on a novel deep learning architecture, able to analyse the involved signals, verifying and validating the behaviour of the ADAS. We introduce a novel deep learning model, discuss its architecture, and present extensive experimental results that clearly show that our approach outperforms current state-of-the-art models in time series classification and the traditional rule-based approaches for ADAS verification and validation. Our contribution is three-fold: (i) we present the first non rule-based solution for ADAS scenario classification based on our state-space model variant; (ii) we introduce a novel dedicated two-branch architecture with cross-temporal interaction and adaptive gating fusion, designed to simultaneously capture long- and short-term temporal dependencies in complex multivariate time series; (iii) we propose a lightweight yet effective solution that outperforms the state-of-the-art approaches while maintaining a significantly reduced parameters count and computational cost in terms of FLOPS (Floating Point Operations Per Second).

The increase in consumer expectations in terms of comfort and safety accelerated the development of Advanced Driver Assistance Systems (ADAS), which represent an intermediate but fundamental step towards complete vehicle automation. In parallel, the progress in the field of data-driven algorithms and machine learning has allowed for important advancements in the research and development of autonomous driving systems. We focus on the verification and validation of the software for ADAS, with the objective of ensuring compliance with international regulations and safety standards, and propose a solution that aims to overcome traditional rule-based approaches for the validation of ADAS functionalities. In particular, we investigate an automated validation process based on a novel deep learning architecture, able to analyse the involved signals, verifying and validating the behaviour of the ADAS. We introduce a novel deep learning model, discuss its architecture, and present extensive experimental results that clearly show that our approach outperforms current state-of-the-art models in time series classification and the traditional rule-based approaches for ADAS verification and validation. Our contribution is three-fold: (i) we present the first non rule-based solution for ADAS scenario classification based on our state-space model variant; (ii) we introduce a novel dedicated two-branch architecture with cross-temporal interaction and adaptive gating fusion, designed to simultaneously capture long- and short-term temporal dependencies in complex multivariate time series; (iii) we propose a lightweight yet effective solution that outperforms the state-of-the-art approaches while maintaining a significantly reduced parameters count and computational cost in terms of FLOPS (Floating Point Operations Per Second).