Politecnio die Bari - Catalogo di prodotti della Ricerca
Not a member yet
36616 research outputs found
Sort by
A Serverless Cloud-to-Thing Framework for TinyMLOps Workflows
No full textThe deployment of Machine Learning (ML) across the Cloud-to-Thing continuum is a significant challenge, particularly when considering the heterogeneity of the available devices. This work introduces a general- purpose framework for Tiny Machine Learning Operations (TinyMLOps) that enables the orchestration of ML workflows in distributed, serverless environments spanning cloud, edge, and Internet of Things (IoT) nodes. The architecture follows an event-driven model in which each node—depending on its capabilities—implements a minimal mandatory set of components and an optional set of extended functionalities. Nodes advertise their capabilities and collaboratively fulfill MLOps tasks by handling requests they can satisfy. This decentralized approach allows for dynamic, context-aware distribution of operations across networks of heterogeneous resource- constrained devices. The framework is validated by means of a prototype implementation and early experiments involving STM32-based microcontrollers and Raspberry Pi edge devices
Scan and 3D Print: Magnetic Resonance Imaging‐Guided, Monolithic Desktop Fabrication of Highly Biomimetic Skeletal System of the Human Hand
No full text3D-printed human-inspired hands, while visually similar to their biological counterparts, often lack key features that enable the unique capabilities of human hands. In this research, a framework for desktop 3D printing patient-specific human hands with a high functional level of biomimicry is presented. Magnetic resonance imaging (MRI) data are used to create computer aided design (CAD) models replicating key features of the skeletal system, including soft joints, ligaments, and volar plates, which are critical for mimicking the motions and functions of natural hands. The entire hand, consisting of rigid and soft segments, is monolithically 3D-printed using a commercial, inexpensive (≈€ 500) desktop multimaterial printer, eliminating the need for assembly and expensive 3D printers. The proposed MRI to Desktop 3D printing approach contrasts with the state of the art, where high biomimicry is achieved through a multistage assembly process and expensive 3D printing setups. The resulting hand shows several unique behaviors of natural hands, including an opposable thumb moving across the palm, improved resistance at bone–joint interfaces, high life cycle, constrained bending, absorption of perpendicular loads, high range of coordinated, bioinspired motion, and grasping capabilities. The proposed approach can be potentially used to 3D print prosthetic hands tailored to individual needs, leveraging patient-specific digitally created MRI data
Influence of Structural Damping Uncertainty on Damping Reduction Factor
No full textIn practice, elastic response spectra are generally obtained by utilizing the 5% value for the damping ratio. The Damping Reduction Factor (DRF) allows to account for higher damping values. As proved by many literature studies, the DRF mainly depends on the structural damping ratio, until now essentially treated in a deterministic way. In this framework, the main aim of the present study is to explore a new definition of DRF including the effects of probabilistic uncertainties. Uncertainty is incorporated in both the random process, adopted to model the dynamic input, and the damping coefficient, introduced in the analysis as an uncertain variable
How to Build a Digital Twin for Operating PEM-Electrolyser System – A Reference Approach
No full textOperating electrolyzers for producing green hydrogen is a critical emerging issue because of either the broader use of hydrogen for several scopes or the short life span and efficiency of these components. Digital Twin offers a new opportunity to effectively face these problems by improving online control and providing fault detection, diagnosis, and prediction services. Since the Digital Twin is, in fact, a virtual mirror of a real system continuously updated by information received from the field, it allows it to swiftly react to small signals of departure from standard or optimal conditions. Although digital twins are widely applied in different fields, comprehensive guidance on developing and designing a digital twin in the literature is still lacking. This manuscript aims to provide a comprehensive guide on how to build the Digital Twin of a PEM-Electrolyzer. In particular, the architecture of the digital twin is initially presented, then all its components are analyzed, showing the steps to be performed to build a Digital Twin for operating PEM-Electrolyser system
Beneath the Surface: How Climate Change Intensifies Erosion and Suspended Sediment Loads
No full textThis study leverages high-resolution climate datasets and advanced hydrodynamic modelling tools to propose a methodological procedure for assessing the potential impact of changes in atmospheric patterns on marine bottom stress and erosion processes occurring on the seabed. The analysis focuses on the Mar Piccolo basin of Taranto, a coastal area in southern Italy where marine sediments are heavily impacted by both past and ongoing anthropogenic pollution. Hydrodynamic simulations performed to define medium-term future scenarios indicate that, starting from 2035, a marked increase
in current intensity is expected in both surface and bottom layers. This shift in current dynamics can be mainly attributed to changes in the wind regime. The enhanced current intensity is expected to lead to stronger shear stresses at the sediment-water interface, exceeding the critical thresholds for sediment resuspension, favouring sediment mobilization. These outcomes highlight the importance of analysing climate-related processes for understanding expected coastal dynamics and designing targeted remediation strategies for contaminated coastal sites
A Simulation-as-a-Service Engine for Urban Mobility Digital Twins
No full textThe Urban Digital Twin (UDT) paradigm is increasingly adopted to monitor and simulate transport networks for smart city mobility planning and policy-making, as well as for analyzing the integration of innovative transportation technologies and services. Although several mature traffic simulators are available, their integration into broader UDT systems is still limited due to the lack of standardized APIs for scenario definition, management and execution. This paper presents a REST API designed to integrate the SUMO traffic simulator into UDT systems for smart cities, adopting a simulation-as-a-service approach. The proposed framework encapsulates SUMO and exposes its functionalities through an HTTP-based web API, enabling real-time simulation control, scenario modification, and data retrieval. This approach facilitates the development of UDTs which support planning, monitoring, and interactive what-if scenario analysis within microservice architectures. The paper presents integration guidelines of the proposed framework into UDT platforms for smart cities and early experimental evaluations for performance and scalability assessment