Archivio della ricerca - Fondazione Bruno Kessler
Not a member yet
21227 research outputs found
Sort by
A Fuzzy Decision Support System to Optimize Irrigation Practices in Trentino Region
No full textThis paper presents the development and evaluation of a Fuzzy Decision Support System for irrigation management to promote sustainable water use in precision agriculture. A Mamdani-type fuzzy logic model was designed to optimize irrigation scheduling for vineyards in the Val d’Adige region of Trentino, Italy. The system integrates expert knowledge with real-time data from tensiometers and weather stations to generate adaptive, site-specific recommendations. Bayesian optimization was used to fine-tune the membership functions of fuzzy variables, enhancing system performance. Field evaluations conducted in 2023 across multiple sectors assessed total water use, average soil moisture, and days exceeding critical moisture thresholds. Results show that the system reduced total water consumption by over 52% compared to traditional methods while maintaining soil moisture within optimal levels. These findings underscore the potential of combining fuzzy logic and IoT-based sensing to support scalable, adaptive irrigation strategies across various crops and regions
Rethinking NIDS Rule-Based Pre-Filtering
No full textSurging network traffic is pushing signature-based Network Intrusion Detection Systems (NIDSs) to their limits, as they struggle to inspect every incoming packet. The high computational cost of analyzing each packet and matching it against large rulesets can lead to system saturation and missed attacks. Rule-based pre-filtering can reduce this cost by forwarding only potentially malicious packets to the NIDS. However, existing work has largely overlooked the impact of pre-filtering on the NIDS’s attack detection performance. Our analysis shows that current methods disrupt attack detection because they discard packets that do not match the pre-filtering rules, ignoring the fact that NIDSs require additional flow information (e.g., the TCP handshake) beyond the malicious packets to process flows and detect attacks properly. To address this, we propose erBF, a new rule-based pre-filtering approach that pre-filters traffic not only according to the rules but also based on the NIDSs’ flow processing requirements. Experimental results with Snort demonstrate that eRBF achieves the desired balance, forwarding less than 22% of all packets across two well-known datasets while maintaining the attack detection above 95%
Understanding is Seeing: Metaphorical and Visual Reasoning in Multimodal Large Language Models
No full text
Renderworld: World Model with Self-Supervised 3D Label
No full textEnd-to-end autonomous driving with vision-only is not only more cost-effective compared to LiDAR-vision fusion but also more reliable than traditional methods. To achieve a economical and robust purely visual autonomous driving system, we propose RenderWorld, a vision-only end-to-end autonomous driving framework, which generates 3D occupancy labels using a self-supervised gaussian-based Img2Occ Module, then encodes the labels by AM-VAE, and uses world model for forecasting and planning. RenderWorld employs Gaussian Splatting to represent 3D scenes and render 2D images greatly improves segmentation accuracy and reduces GPU memory consumption compared with NeRF-based methods. By applying AM-VAE to encode air and non-air separately, RenderWorld achieves more fine-grained scene element representation, leading to state-of-the-art performance in both 4D occupancy forecasting and motion planning from autoregressive world model
Leveraging Contracts for Failure Monitoring and Identification in Automated Driving Systems
No full textAs the deployment of AI agents in Automated Driving Systems (ADS) becomes increasingly prevalent, ensuring their safety and reliability is of paramount importance. This paper presents a novel approach to enhance the safety assurance of automated driving systems by employing formal contracts to specify and refine system-level properties. The proposed framework leverages formal methods to specify contracts that capture the expected behavior of perception and control components in ADS. These contracts serve as a basis for systematically validating system behavior against safety requirements during design and testing phases. We demonstrate the efficacy of our approach using the CARLA simulator and an off-the-shelf AI agent. By monitoring the components contracts on the ADS simulation, we could identify not only the cause of system failures, but also the situations which could lead to a system failure, facilitating the debugging and maintenance of the AI agents
Ion implantation through a screening layer for shallow NV center formation in diamond for quantum sensing applications
No full textShallow nitrogen-vacancy (NV−) centers in diamond are of significant interest for high precision quantum sensing applications, like single biological imaging and environmental sensing [1]. When located within few nanometers (< 10 nm) from the diamond surface, the increased strength of their interaction makes their quantum properties, such as spin polarization, highly sensitive to local variation in external electromagnetic fields and temperature fluctuation at the surface. This proximity enhances therefore their potential for high-sensitive nanoscale sensing and mapping. In addition, the shallow position makes NV- centers advantageous for integration into compact nanoscale devices [2]. Various strategies have been explored to fabricate shallow NV- centers. This study presents the results of a methodology combining medium-energy broad-beam ion implantation at two different angles and a screening layer to control and reduce the penetration depth of ions into the diamond. Monte Carlo simulations (SRIM) predicted shallow nitrogen implantation depths, which were experimentally confirmed through angle-resolved X-ray photoelectron spectroscopy (ARXPS). Confocal photoluminescence (PL) mapping further highlighted how the implantation angle and the screening layer modulate the density of formed shallow NV− centers, as measured by PL emission intensities. Single-point PL spectroscopy revealed distinct variations in the NV0 to NV- emission ratio, attributed to differing charge neutralization rates influenced by implantation conditions and the resulting proximity of NV- centers to the surface. Based on the experimental findings, strategies for improving the efficiency and uniformity of formation of shallow NV− centers are discussed
Fidelity Estimation of Linear Pixel Array Photon Number Detectors
No full textPhoton-number-resolving detectors (PNRDs) are key devices for quantum optics, employed in applications such as photon measurements in the number basis [1], quantum key exchange [2], photon-counting laser radar [3] and quality checking of single-photon sources [4]
Towards Cryptography Bill of Materials Compliance
No full textDiscovering, managing, and reporting on cryptographic as-
sets is a critical step for the transition to quantum-safe systems and
applications. Cryptography Bills of Materials (CBOMs) have been pro-
posed as an aid to cryptographic inventory, agility, and compliance with
guidelines to create more secure software and services.
Writing policies and automating compliance checks for cryptography is a
valuable but complex task. We present a prototype framework for auto-
mated evaluation of cryptographic compliance extending existing CBOM
tools with a policy-driven engine that classifies cryptographic assets ac-
cording to customizable rules and compliance levels. Machine-readable
policies enable flexible adaptation to different guidelines while support-
ing analysts in performing semi-automatic assessments.
The prototype is validated through experiments on both synthetic and
real-world software. Results show that the system correctly identifies
deprecated and disallowed primitives, producing clear compliance re-
ports. While we highlight some difficulties common to automating com-
pliance checks, our findings demonstrate the potential of CBOM-based
approaches to enhance visibility, governance, and readiness for the post-
quantum cryptography transition