26 August 2024 in Engineering Applications of Artificial Intelligence
29 November 2023 in IEEE Transactions on Industrial Cyber-Physical Systems
Industrial Cyber-Physical Systems (ICPSs) generate cyber and physical data whose joint elaboration can provide insight into ICPSs' operating conditions. Cyber-Physical Anomaly Detection (CPAD) addresses the joint analysis of cyber and physical threats through multi-source and multi-modal data analysis. CPAD is often tailored to specific anomaly types and may use opaque deep learning models, impairing flexibility and explainability. In light of these challenges, we propose a two-level fusion framework for modeling and deploying CPAD in distributed ICPSs. The first detector-level fusion involves deploying CPAD detectors to several distributed ICPS segments and training them through data/decision fusion techniques with historical cyber-physical data. When the distributed ICPS is operational, thus collecting new cyber-physical data, ICPS segments' trained CPAD detectors provide pieces of evidence that go through the second ensemble-level fusion, for which we propose an explainable decision fusion technique based on Time-Varying Dynamic Bayesian networks. The evaluation involves the comprehensive application of the framework to a real hardware-in-the-loop case-study in a laboratory environment. The proposed ensemble-level fusion outperforms the state-of-the-art decision fusion techniques while providing explainable results.
14 October 2024 in IEEE Transactions on Industrial Informatics
Digital twin development of industrial cyber-physical systems requires modeling, simulation, and monitoring to provide accurate digital replicas mimicking system dynamics. To this aim, modern solutions employ data-driven approaches to capture normal system dynamics using historical data, and anomaly detection using run-time data. However, these approaches are typically process-agnostic and have limited explainability, which negatively impacts trustworthiness. Hence, we propose a novel framework for the digital twin development of industrial cyber-physical systems based on process mining, which connects data-driven and process-based analyses. The framework implements an offline phase that systematically identifies the most suitable process model to capture normal dynamics and simulates faulty dynamics for what-if analysis. The subsequent online phase involves run-time monitoring for anomaly detection. We develop a proof-of-concept application of the framework addressing a water distribution case study that allows physical fault injection. Results highlight the importance of adopting high-quality process models to significantly improve anomaly detection and time performance.
12 April 2021 in Knowledge and Information Systems
So far, multiple classifier systems have been increasingly designed to take advantage of hardware features, such as high parallelism and computational power. Indeed, compared to software implementations, hardware accelerators guarantee higher throughput and lower latency. Although the combination of multiple classifiers leads to high classification accuracy, the required area overhead makes the design of a hardware accelerator unfeasible, hindering the adoption of commercial configurable devices. For this reason, in this paper, we exploit approximate computing design paradigm to trade hardware area overhead off for classification accuracy. In particular, starting from trained DT models and employing precision-scaling technique, we explore approximate decision tree variants by means of multiple objective optimization problem, demonstrating a significant performance improvement targeting field-programmable gate array devices.
27 June 2006 in Journal of Grid Computing