PORTO @ Archivio Istituzionale della Ricerca

Vectorized in-Place CRC: a Zero Memory-Overhead Fault Detection Scheme for QNNs on RISC-V

Reliability against memory-induced transient faults is a critical requirement for quantized neural networks (QNNs) deployed in safety-critical edge environments. This paper proposes an in-place fault detection strategy that embeds Cyclic Redundancy Check (CRC) codes directly into the Least Significant Bits (LSBs) of 8-bit quantized weights, achieving zero storage overhead by repurposing weight precision for granular reliability. The scheme leverages a vectorized routine optimized for the RISC...

Development of Bearing Fault Detection Models using Multibody Simulation Training Data

This study evaluates the performance of simulation-trained fault detection models on large spherical roller bearings vibration data. A high-fidelity multibody (MB) model of a SKF 22240 CCK/W33 bearing is developed through Simscape Multibody to reproduce the coupled dynamics of inner and outer rings, cage, and 38 rolling elements. Localized defects on raceways are represented through a pointcloud contact formulation, where selected nodes are radially displaced to emulate faults. The model outp...

Mapping Personas to Text Transformations: A Taxonomy Outline for Content Adaptation

Tailoring writings to specific audiences increases engagement and comprehension, and LLMs with persona-based adaptation can make this process easier and scalable. However, current systems treat personas as a black-box prompt modifier: non-expert users can specify "simplify for a beginner" or "adapt for an expert", but cannot inspect how and what persona traits map to concrete textual edits. This opacity limits control, and prevents systematic understanding of what makes adaptations effective....

An Edge AI Industrial Environment Supporting Reliability Assessment and Enhancement